Paper Digest: NeurIPS 2021 Highlights
Download NIPS-2021-Paper-Digests.pdf– Highlights of all NeurIPS-2021 papers. Readers can choose to read all these highlights on our console, which allows users to filter out papers using keywords and find related papers, patents, etc. In addition, we identified a large number of papers that have published their code and data. Here is the NeurIPS 2021 Papers with Code/Data page. You may also like to explore our “Best Paper” Digest (NIPS), which lists the most influential NIPS papers in the last 30 years. The Conference on Neural Information Processing Systems (NIPS) is one of the top machine learning conferences in the world. In 2021, it is to be held online due to coivd-19 pandemic.
To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights / summaries to quickly get the main idea of each paper. Based in New York, Paper Digest is dedicated to producing high-quality text analysis results that people can acturally use on a daily basis. In the past 4 years, we have been serving users across the world with a number of exclusive services on ranking, search, tracking and review. This month we feature Literature Review Generator, which automatically generates literature review around any topic.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: NeurIPS 2021 Highlights
| Paper | Author(s) | Code | |
|---|---|---|---|
| 1 | Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. |
Christoph Dann; Teodor Vanislavov Marinov; Mehryar Mohri; Julian Zimmert; | |
| 2 | Learning One Representation to Optimize All Rewards Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. |
Ahmed Touati; Yann Ollivier; | |
| 3 | Matrix Factorisation and The Interpretation of Geodesic Distance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given a graph or similarity matrix, we consider the problem of recovering a notion of true distance between the nodes, and so their true positions. |
Nick Whiteley; Annie Gray; Patrick Rubin-Delanchy; | |
| 4 | UniDoc: Unified Pretraining Framework for Document Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present UniDoc, a new unified pretraining framework for document understanding. |
Jiuxiang Gu; Jason Kuen; Vlad Morariu; Handong Zhao; Rajiv Jain; Nikolaos Barmpalios; Ani Nenkova; Tong Sun; | |
| 5 | Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To find the answer, we propose a new diagnostic tool — Filter Attribution method based on Integral Gradient (FAIG). |
Liangbin Xie; Xintao Wang; Chao Dong; Zhongang Qi; Ying Shan; | |
| 6 | Counterfactual Explanations Can Be Manipulated Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce the first framework that describes the vulnerabilities of counterfactual explanations and shows how they can be manipulated. |
Dylan Slack; Anna Hilgard; Himabindu Lakkaraju; Sameer Singh; | |
| 7 | From Canonical Correlation Analysis to Self-supervised Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. |
Hengrui Zhang; Qitian Wu; Junchi Yan; David Wipf; Philip S. Yu; | |
| 8 | BAST: Bayesian Additive Regression Spanning Trees for Complex Constrained Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article proposes a Bayesian additive regression spanning trees (BAST) model for nonparametric regression on manifolds, with an emphasis on complex constrained domains or irregularly shaped spaces embedded in Euclidean spaces. |
Zhao Tang Luo; Huiyan Sang; Bani Mallick; | |
| 9 | Hyperbolic Busemann Learning with Ideal Prototypes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Hyperbolic Busemann Learning. The main idea behind our approach is to position prototypes on the ideal boundary of the Poincar\'{e} ball, which does not require prior label knowledge. |
Mina Ghadimi Atigh; Martin Keller-Ressel; Pascal Mettes; | |
| 10 | Backward-Compatible Prediction Updates: A Probabilistic Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize the Prediction Update Problem and present an efficient probabilistic approach as answer to the above questions. |
Frederik Tr�uble; Julius von K�gelgen; Matth�us Kleindessner; Francesco Locatello; Bernhard Sch�lkopf; Peter Gehler; | |
| 11 | Truncated Marginal Neural Ratio Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a neural simulation-based inference algorithm which simultaneously offers simulation efficiency and fast empirical posterior testability, which is unique among modern algorithms. |
Benjamin Miller; Alex Cole; Patrick Forr�; Gilles Louppe; Christoph Weniger; | |
| 12 | ReAct: Out-of-distribution Detection With Rectified Activations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose ReAct—a simple and effective technique for reducing model overconfidence on OOD data. |
Yiyou Sun; Chuan Guo; Sharon Li; | |
| 13 | Non-local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new set of non-local relations in order to characterize long-range latent pose interactions, unlike general contrastive relations where positive couplings are limited to a local neighborhood structure. |
Jogendra Nath Kundu; Siddharth Seth; Anirudh Jamkhandi; Pradyumna YM; Varun Jampani; Anirban Chakraborty; Venkatesh Babu R; | |
| 14 | Fast Training of Neural Lumigraph Representations Using Meta Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by neural variants of image-based rendering, we develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time. |
Alexander Bergman; Petr Kellnhofer; Gordon Wetzstein; | |
| 15 | Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use dynamical mean field theory techniques to describe analytically the average dynamics of these methods in a prototypical non-convex model: the (spiked) matrix-tensor model. |
Stefano Sarao Mannelli; Pierfrancesco Urbani; | |
| 16 | Multimodal Few-Shot Learning with Frozen Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present a simple, yet effective, approach for transferring this few-shot learning ability to a multimodal setting (vision and language). |
Maria Tsimpoukelli; Jacob Menick; Serkan Cabi; S. M. Ali Eslami; Oriol Vinyals; Felix Hill; | |
| 17 | Approximating The Permanent with Deep Rejection Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a randomized approximation scheme for the permanent of a matrix with nonnegative entries. |
Juha Harviainen; Antti R�ysk�; Mikko Koivisto; | |
| 18 | Revisiting Model Stitching to Compare Neural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit and extend model stitching (Lenc & Vedaldi 2015) as a methodology to study the internal representations of neural networks. |
Yamini Bansal; Preetum Nakkiran; Boaz Barak; | |
| 19 | AugMax: Adversarial Composition of Random Augmentations for Robust Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we propose a data augmentation framework, termed AugMax, to unify the two aspects of diversity and hardness. |
Haotao N. Wang; Chaowei Xiao; Jean Kossaifi; Zhiding Yu; Anima Anandkumar; Zhangyang Wang; | code |
| 20 | Habitat 2.0: Training Home Assistants to Rearrange Their Habitat Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. |
Andrew Szot; Alexander Clegg; Eric Undersander; Erik Wijmans; Yili Zhao; John Turner; Noah Maestre; Mustafa Mukadam; Devendra Singh Chaplot; Oleksandr Maksymets; Aaron Gokaslan; Vladim�r Vondru�; Sameer Dharur; Franziska Meier; Wojciech Galuba; Angel Chang; Zsolt Kira; Vladlen Koltun; Jitendra Malik; Manolis Savva; Dhruv Batra; | |
| 21 | Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we seek to find a $\delta$-invariant algorithm for policy gradient (PG) methods, which performs well regardless of the value of $\delta$. |
Seohong Park; Jaekyeom Kim; Gunhee Kim; | code |
| 22 | Meta-Learning Reliable Priors in The Function Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Addressing these shortcomings, we introduce a novel meta-learning framework, called F-PACOH, that treats meta-learned priors as stochastic processes and performs meta-level regularization directly in the function space. |
Jonas Rothfuss; Dominique Heyn; jinfan Chen; Andreas Krause; | |
| 23 | VoiceMixer: Adversarial Voice Style Mixup Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present VoiceMixer which can effectively decompose and transfer voice style through a novel information bottleneck and adversarial feedback. |
Sang-Hoon Lee; Ji-Hoon Kim; Hyunseung Chung; Seong-Whan Lee; | |
| 24 | Predicting What You Already Know Helps: Provable Self-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper posits a mechanism based on approximate conditional independence to formalize how solving certain pretext tasks can learn representations that provably decrease the sample complexity of downstream supervised tasks. |
Jason D. Lee; Qi Lei; Nikunj Saunshi; JIACHENG ZHUO; | |
| 25 | Oracle Complexity in Nonsmooth Nonconvex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study nonsmooth nonconvex optimization from an oracle complexity viewpoint, where the algorithm is assumed to be given access only to local information about the function at various points. |
Guy Kornowski; Ohad Shamir; | |
| 26 | CentripetalText: An Efficient Text Instance Representation for Scene Text Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient text instance representation named CentripetalText (CT), which decomposes text instances into the combination of text kernels and centripetal shifts. |
Tao Sheng; Jie Chen; Zhouhui Lian; | |
| 27 | Learning to Select Exogenous Events for Marked Temporal Point Process Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To thisend, our goal in this paper is to identify the set of exogenous events from a set ofunlabelled events. |
Ping Zhang; Rishabh Iyer; Ashish Tendulkar; Gaurav Aggarwal; Abir De; | |
| 28 | DRIVE: One-bit Distributed Mean Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem where $n$ clients transmit $d$-dimensional real-valued vectors using $d(1+o(1))$ bits each, in a manner that allows the receiver to approximately reconstruct their mean. |
Shay Vargaftik; Ran Ben-Basat; Amit Portnoy; Gal Mendelson; Yaniv Ben-Itzhak; Michael Mitzenmacher; | |
| 29 | Learning Space Partitions for Path Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a novel formal regret analysis for when and why such an adaptive region partitioning scheme works. |
Kevin Yang; Tianjun Zhang; Chris Cummins; Brandon Cui; Benoit Steiner; Linnan Wang; Joseph E. Gonzalez; Dan Klein; Yuandong Tian; | code |
| 30 | Progressive Feature Interaction Search for Deep Sparse Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we approach this problem with neural architecture search by automatically searching the critical component in DSNs, the feature-interaction layer. |
Chen Gao; Yinfeng Li; Quanming Yao; Depeng Jin; Yong Li; | |
| 31 | Local Explanation of Dialogue Response Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study model-agnostic explanations of a representative text generation task — dialogue response generation. |
Yi-Lin Tuan; Connor Pryor; Wenhu Chen; Lise Getoor; William Yang Wang; | |
| 32 | Scalable Inference in SDEs By Direct Matching of The Fokker-Planck-Kolmogorov Equation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this issue by revisiting the classical SDE literature and derive direct approximations to the (typically intractable) Fokker–Planck–Kolmogorov equation by matching moments. |
Arno Solin; Ella Tamir; Prakhar Verma; | |
| 33 | The Complexity of Bayesian Network Learning: Revisiting The Superstructure Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the parameterized complexity of Bayesian Network Structure Learning (BNSL), a classical problem that has received significant attention in empirical but also purely theoretical studies. |
Robert Ganian; Viktoriia Korchemna; | |
| 34 | Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an efficient low-rank approximation algorithm for non-negative tensors. |
Kazu Ghalamkari; Mahito Sugiyama; | |
| 35 | Learning Stochastic Majority Votes By Minimizing A PAC-Bayes Generalization Bound Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties. |
Valentina Zantedeschi; Paul Viallard; Emilie Morvant; R�mi Emonet; Amaury Habrard; Pascal Germain; Benjamin Guedj; | |
| 36 | Numerical Influence of ReLU'(0) on Backpropagation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the importance of the value of ReLU'(0) for several precision levels (16, 32, 64 bits), on various networks (fully connected, VGG, ResNet) and datasets (MNIST, CIFAR10, SVHN, ImageNet). |
David Bertoin; J�r�me Bolte; S�bastien Gerchinovitz; Edouard Pauwels; | |
| 37 | A Contrastive Learning Approach for Training Variational Autoencoder Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we propose an energy-based prior defined by the product of a base prior distribution and a reweighting factor, designed to bring the base closer to the aggregate posterior. |
Jyoti Aneja; Alex Schwing; Jan Kautz; Arash Vahdat; | |
| 38 | What Training Reveals About Neural Network Complexity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training dynamics. |
Andreas Loukas; Marinos Poiitis; Stefanie Jegelka; | |
| 39 | Class-agnostic Reconstruction of Dynamic Objects from Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos. |
Zhongzheng Ren; Xiaoming Zhao; Alex Schwing; | |
| 40 | Unique Sparse Decomposition of Low Rank Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the problem of seeking a unique decomposition of a low-rank matrix $Y\in \mathbb{R}^{p\times n}$ that admits a sparse representation. |
Dian Jin; Xin Bing; Yuqian Zhang; | |
| 41 | Neighborhood Reconstructing Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To simultaneously address the two issues of overfitting and local connectivity, we propose a new graph-based autoencoder, the Neighborhood Reconstructing Autoencoder (NRAE). |
Yonghyeon LEE; Hyeokjun Kwon; Frank Park; | code |
| 42 | TopicNet: Semantic Graph-Guided Topic Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as inductive bias to influence the learning. |
Zhibin Duan; Yi.shi Xu; Bo Chen; dongsheng wang; Chaojie Wang; Mingyuan Zhou; | |
| 43 | (Almost) Free Incentivized Exploration from Decentralized Learning Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we break this barrier and study incentivized exploration with multiple and long-term strategic agents, who have more complicated behaviors that often appear in real-world applications. |
Chengshuai Shi; Haifeng Xu; Wei Xiong; Cong Shen; | |
| 44 | Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a simple sequence model inspired by control systems that generalizes these approaches while addressing their shortcomings. |
Albert Gu; Isys Johnson; Karan Goel; Khaled Saab; Tri Dao; Atri Rudra; Christopher R�; | |
| 45 | Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. |
Zifeng Wang; Tong Jian; Aria Masoomi; Stratis Ioannidis; Jennifer Dy; | |
| 46 | T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new prior for high-dimensional parameters with graphical relations, referred to as the Tree-based Low-rank Horseshoe (T-LoHo) model, that generalizes the popular univariate Bayesian horseshoe shrinkage prior to the multivariate setting to detect structured sparsity and smoothness simultaneously. |
Changwoo Lee; Zhao Tang Luo; Huiyan Sang; | |
| 47 | The Utility of Explainable AI in Ad Hoc Human-Machine Teaming Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present two novel human-subject experiments quantifying the benefits of deploying xAI techniques within a human-machine teaming scenario. |
Rohan Paleja; Muyleng Ghuy; Nadun Ranawaka Arachchige; Reed Jensen; Matthew Gombolay; | |
| 48 | Subgoal Search For Complex Reasoning Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. |
Konrad Czechowski; Tomasz Odrzyg�zdz; Marek Zbysinski; Michal Zawalski; Krzysztof Olejnik; Yuhuai Wu; Lukasz Kucinski; Piotr Milos; | |
| 49 | MCMC Variational Inference Via Uncorrected Hamiltonian Annealing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework to use an AIS-like procedure with Uncorrected Hamiltonian MCMC, called Uncorrected Hamiltonian Annealing. |
Tomas Geffner; Justin Domke; | |
| 50 | Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the cross-modal alignment challenge from a fine-grained perspective. |
Keji He; Yan Huang; Qi Wu; Jianhua Yang; Dong An; Shuanglin Sima; Liang Wang; | code |
| 51 | A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To answer this question, we perform a large-scale analysis of popular model compression techniques which uncovers several intriguing patterns. |
James Diffenderfer; Brian Bartoldson; Shreya Chaganti; Jize Zhang; Bhavya Kailkhura; | code |
| 52 | On The Importance of Gradients for Detecting Distributional Shifts in The Wild Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present GradNorm, a simple and effective approach for detecting OOD inputs by utilizing information extracted from the gradient space. |
Rui Huang; Andrew Geng; Sharon Li; | |
| 53 | Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that approximately preserves the answers to a large collection of statistical queries. |
Terrance Liu; Giuseppe Vietri; Steven Z. Wu; | |
| 54 | Understanding End-to-End Model-Based Reinforcement Learning Methods As Implicit Parameterization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore such implicit representations of value functions via theory and focused experimentation. |
Clement Gehring; Kenji Kawaguchi; Jiaoyang Huang; Leslie Kaelbling; | |
| 55 | Mirror Langevin Monte Carlo: The Case Under Isoperimetry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the connection between sampling and optimization, we study a mirror descent analogue of Langevin dynamics and analyze three different discretization schemes, giving nonasymptotic convergence rate under functional inequalities such as Log-Sobolev in the corresponding metric. |
Qijia Jiang; | |
| 56 | Do Different Tracking Tasks Require Different Appearance Models? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. |
Zhongdao Wang; Hengshuang Zhao; Ya-Li Li; Shengjin Wang; Philip Torr; Luca Bertinetto; | |
| 57 | Towards Robust Vision By Multi-task Learning on Monkey Visual Cortex Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we successfully leveraged these inductive biases with a multi-task learning approach: we jointly trained a deep network to perform image classification and to predict neural activity in macaque primary visual cortex (V1) in response to the same natural stimuli. |
Shahd Safarani; Arne Nix; Konstantin Willeke; Santiago Cadena; Kelli Restivo; George Denfield; Andreas Tolias; Fabian Sinz; | |
| 58 | Arbitrary Conditional Distributions with Energy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method, Arbitrary Conditioning with Energy (ACE), that can simultaneously estimate the distribution $p(\mathbf{x}_u \mid \mathbf{x}_o)$ for all possible subsets of unobserved features $\mathbf{x}_u$ and observed features $\mathbf{x}_o$. |
Ryan Strauss; Junier B. Oliva; | |
| 59 | Learning Domain Invariant Representations in Goal-conditioned Block MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study this problem for goal-conditioned RL agents. |
Beining Han; Chongyi Zheng; Harris Chan; Keiran Paster; Michael Zhang; Jimmy Ba; | |
| 60 | Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop efficient algorithms for optimizing different objective functions quantifying the informativeness of a budget-constrained batch of experiments. |
Scott Sussex; Caroline Uhler; Andreas Krause; | |
| 61 | Fuzzy Clustering with Similarity Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a semi-supervised active clustering framework, where the learner is allowed to interact with an oracle (domain expert), asking for the similarity between a certain set of chosen items. |
Wasim Huleihel; Arya Mazumdar; Soumyabrata Pal; | |
| 62 | Improving Black-box Optimization in VAE Latent Space Using Decoder Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to leverage the epistemic uncertainty of the decoder to guide the optimization process. |
Pascal Notin; Jos� Miguel Hern�ndez-Lobato; Yarin Gal; | |
| 63 | Sample Selection for Fair and Robust Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a sample selection-based algorithm for fair and robust training. |
Yuji Roh; Kangwook Lee; Steven Whang; Changho Suh; | |
| 64 | NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes NeurWIN, a neural Whittle index network that seeks to learn the Whittle indices for any restless bandits by leveraging mathematical properties of the Whittle indices. |
Khaled Nakhleh; Santosh Ganji; Ping-Chun Hsieh; I-Hong Hou; Srinivas Shakkottai; | |
| 65 | Sageflow: Robust Federated Learning Against Both Stragglers and Adversaries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Sageflow, staleness-aware grouping with entropy-based filtering and loss-weighted averaging, to handle both stragglers and adversaries simultaneously. |
Jung Wuk Park; Dong-Jun Han; Minseok Choi; Jaekyun Moon; | |
| 66 | Alias-Free Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. |
Tero Karras; Miika Aittala; Samuli Laine; Erik H�rk�nen; Janne Hellsten; Jaakko Lehtinen; Timo Aila; | |
| 67 | Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising Without Clean Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, here we present a novel approach, called Noise2Score, which reveals a missing link in order to unite these seemingly different approaches.Specifically, we show that image denoising problems without clean images can be addressed by finding the mode of the posterior distribution and that the Tweedie’s formula offers an explicit solution through the score function (i.e. the gradient of loglikelihood). |
Kwanyoung Kim; Jong Chul Ye; | |
| 68 | Continuous Mean-Covariance Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Continuous Mean-Covariance Bandit (CMCB) model to explicitly take into account option correlation. |
Yihan Du; Siwei Wang; Zhixuan Fang; Longbo Huang; | |
| 69 | Dynamic Visual Reasoning By Learning Differentiable Physics Models from Video and Language Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects and their interactions from videos and language. |
Mingyu Ding; Zhenfang Chen; Tao Du; Ping Luo; Josh Tenenbaum; Chuang Gan; | |
| 70 | Solving Soft Clustering Ensemble Via $k$-Sparse Discrete Wasserstein Barycenter Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the more general soft clustering ensemble problem where each individual solution is a soft clustering. |
Ruizhe Qin; Mengying Li; Hu Ding; | |
| 71 | Bayesian Adaptation for Covariate Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters, and show how approximate inference in this model can be instantiated with a simple regularized entropy minimization procedure at test-time. |
Aurick Zhou; Sergey Levine; | |
| 72 | Perturb-and-max-product: Sampling and Learning in Discrete Energy-based Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present perturb-and-max-product (PMP), a parallel and scalable mechanism for sampling and learning in discrete EBMs. |
Miguel Lazaro-Gredilla; Antoine Dedieu; Dileep George; | |
| 73 | Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we summarize previous concepts of diversity and work towards offering a unified measure of diversity in multi-agent open-ended learning to include all elements in Markov games, based on both Behavioral Diversity (BD) and Response Diversity (RD). |
Xiangyu Liu; Hangtian Jia; Ying Wen; Yaodong Yang; Yujing Hu; Yingfeng Chen; Changjie Fan; ZHIPENG HU; | |
| 74 | Towards Better Understanding of Training Certifiably Robust Models Against Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of training certifiably robust models against adversarial examples. |
Sungyoon Lee; WOOJIN LEE; Jinseong Park; Jaewook Lee; | code |
| 75 | Mitigating Covariate Shift in Imitation Learning Via Offline Data With Partial Coverage Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Model-based IL from Offline data (MILO): an algorithmic framework that utilizes the static dataset to solve the offline IL problem efficiently both in theory and in practice. |
Jonathan Chang; Masatoshi Uehara; Dhruv Sreenivas; Rahul Kidambi; Wen Sun; | code |
| 76 | Global Filter Networks for Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity. |
Yongming Rao; Wenliang Zhao; Zheng Zhu; Jiwen Lu; Jie Zhou; | code |
| 77 | Catastrophic Data Leakage in Vertical Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. |
Xiao Jin; Pin-Yu Chen; Chia-Yi Hsu; Chia-Mu Yu; Tianyi Chen; | code |
| 78 | Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this end, we propose the first FRL framework the convergence of which is guaranteed and tolerant to less than half of the participating agents being random system failures or adversarial attackers. |
Xiaofeng Fan; Yining Ma; Zhongxiang Dai; Wei Jing; Cheston Tan; Bryan Kian Hsiang Low; | |
| 79 | Compacter: Efficient Low-Rank Hypercomplex Adapter Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Compacter, a method for fine-tuning large-scale language models with a better trade-off between task performance and the number of trainable parameters than prior work. |
Rabeeh Karimi Mahabadi; James Henderson; Sebastian Ruder; | code |
| 80 | Distilling Image Classifiers in Object Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we study the case of object detection and, instead of following the standard detector-to-detector distillation approach, introduce a classifier-to-detector knowledge transfer framework. |
Shuxuan Guo; Jose M. Alvarez; Mathieu Salzmann; | |
| 81 | Subgroup Generalization and Fairness of Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel PAC-Bayesian analysis for GNNs under a non-IID semi-supervised learning setup. |
Jiaqi Ma; Junwei Deng; Qiaozhu Mei; | |
| 82 | Scaling Neural Tangent Kernels Via Sketching and Random Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To accelerate learning with NTK, we design a near input-sparsity time approximation algorithm for NTK, by sketching the polynomial expansions of arc-cosine kernels: our sketch for the convolutional counterpart of NTK (CNTK) can transform any image using a linear runtime in the number of pixels. |
Amir Zandieh; Insu Han; Haim Avron; Neta Shoham; Chaewon Kim; Jinwoo Shin; | |
| 83 | BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose BatchQuant, a robust quantizer formulation that allows fast and stable training of a compact, single-shot, mixed-precision, weight-sharing supernet. |
Haoping Bai; Meng Cao; Ping Huang; Jiulong Shan; | |
| 84 | Long Short-Term Transformer for Online Action Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. |
Mingze Xu; Yuanjun Xiong; Hao Chen; Xinyu Li; Wei Xia; Zhuowen Tu; Stefano Soatto; | |
| 85 | Near Optimal Policy Optimization Via REPS Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we aim to fill this gap by providing guarantees and convergence rates for the sub-optimality of a policy learned using first-order optimization methods applied to the REPS objective. |
Aldo Pacchiano; Jonathan Lee; Peter Bartlett; Ofir Nachum; | |
| 86 | Self-Consistent Models and Values Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate a way of augmenting model-based RL, by additionally encouraging a learned model and value function to be jointly \emph{self-consistent}. |
Greg Farquhar; Kate Baumli; Zita Marinho; Angelos Filos; Matteo Hessel; Hado P. van Hasselt; David Silver; | |
| 87 | Learning on Random Balls Is Sufficient for Estimating (Some) Graph Parameters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a theoretical framework for graph classification problems in the partial observation setting (i.e., subgraph samplings). |
Takanori Maehara; Hoang NT; | |
| 88 | Risk-Averse Bayes-Adaptive Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address risk-averse Bayes-adaptive reinforcement learning. |
Marc Rigter; Bruno Lacerda; Nick Hawes; | |
| 89 | Iterative Connecting Probability Estimation for Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a two-stage neighborhood selection procedure to achieve the trade-off between smoothness of the estimate and the ability to discover local structure. |
Yichen Qin; Linhan Yu; Yang Li; | |
| 90 | Learning to Adapt Via Latent Domains for Adaptive Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Alternatively, in this work we break through the standard “source-target” one pair adaptation framework and construct multiple adaptation pairs (e.g. “source-latent” and “latent-target”). |
Yunan Liu; Shanshan Zhang; Yang Li; Jian Yang; | |
| 91 | Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we utilize the {\em predictive normalized maximum likelihood} (pNML) learner, in which no assumptions are made on the tested input. |
Koby Bibas; Meir Feder; Tal Hassner; | |
| 92 | Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation. |
Lei Ke; Xia Li; Martin Danelljan; Yu-Wing Tai; Chi-Keung Tang; Fisher Yu; | code |
| 93 | Algorithmic Instabilities of Accelerated Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the algorithmic stability of Nesterov’s accelerated gradient method. |
Amit Attia; Tomer Koren; | |
| 94 | Learning Optimal Predictive Checklists Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a method to learn checklists for clinical decision support. |
Haoran Zhang; Quaid Morris; Berk Ustun; Marzyeh Ghassemi; | |
| 95 | Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The focus of this paper is on sample complexity guarantees of average-reward reinforcement learning algorithms, which are known to be more challenging to study than their discounted-reward counterparts. |
Sheng Zhang; Zhe Zhang; Siva Theja Maguluri; | |
| 96 | Generalization Bounds for Graph Embedding Using Negative Sampling: Linear Vs Hyperbolic Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a generalization error bound applicable for graph embedding both in linear and hyperbolic spaces under various negative sampling settings that appear in graph embedding. |
Atsushi Suzuki; Atsushi Nitanda; jing wang; Linchuan Xu; Kenji Yamanishi; Marc Cavazza; | |
| 97 | Gradient Starvation: A Learning Proclivity in Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. |
Mohammad Pezeshki; Oumar Kaba; Yoshua Bengio; Aaron C. Courville; Doina Precup; Guillaume Lajoie; | |
| 98 | Offline Reinforcement Learning As One Big Sequence Modeling Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we explore how RL can be reframed as "one big sequence modeling" problem, using state-of-the-art Transformer architectures to model distributions over sequences of states, actions, and rewards. |
Michael Janner; Qiyang Li; Sergey Levine; | |
| 99 | Optimality and Stability in Federated Learning: A Game-theoretic Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we motivate and define a notion of optimality given by the average error rates among federating agents (players). |
Kate Donahue; Jon Kleinberg; | |
| 100 | Understanding Deflation Process in Over-parametrized Tensor Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study the training dynamics for gradient flow on over-parametrized tensor decomposition problems. |
Rong Ge; Yunwei Ren; Xiang Wang; Mo Zhou; | |
| 101 | Privately Learning Subspaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present differentially private algorithms that take input data sampled from a low-dimensional linear subspace (possibly with a small amount of error) and output that subspace (or an approximation to it). |
Vikrant Singhal; Thomas Steinke; | |
| 102 | On The Value of Interaction and Function Approximation in Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce a new problem called confidence set linear classification, that can be used to construct sample-efficient IL algorithms. |
Nived Rajaraman; Yanjun Han; Lin Yang; Jingbo Liu; Jiantao Jiao; Kannan Ramchandran; | |
| 103 | Shapeshifter: A Parameter-efficient Transformer Using Factorized Reshaped Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we focus on factorized representations of matrices that underpin dense, embedding, and self-attention layers. |
Aliakbar Panahi; Seyran Saeedi; Tom Arodz; | |
| 104 | The Adaptive Doubly Robust Estimator and A Paradox Concerning Logging Policy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To obtain an asymptotically normal semiparametric estimator from dependent samples without non-Donsker nuisance estimators, we propose adaptive-fitting as a variant of sample-splitting. |
Masahiro Kato; Kenichiro McAlinn; Shota Yasui; | |
| 105 | Regularized Softmax Deep Multi-Agent Q-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we empirically demonstrate that QMIX, a popular $Q$-learning algorithm for cooperative multi-agent reinforcement learning (MARL), suffers from a more severe overestimation in practice than previously acknowledged, and is not mitigated by existing approaches. |
Ling Pan; Tabish Rashid; Bei Peng; Longbo Huang; Shimon Whiteson; | |
| 106 | Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We train a deep neural network to perform physics-informed downsampling of the terrain map: we optimize the coarse grid representation of the terrain maps, so that the flood prediction will match the fine grid solution. |
Niv Giladi; Zvika Ben-Haim; Sella Nevo; Yossi Matias; Daniel Soudry; | |
| 107 | Systematic Generalization with Edge Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we propose Edge Transformer, a new model that combines inspiration from Transformers and rule-based symbolic AI. |
Leon Bergen; Timothy O'Donnell; Dzmitry Bahdanau; | |
| 108 | TransformerFusion: Monocular RGB Scene Reconstruction Using Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. |
Aljaz Bozic; Pablo Palafox; Justus Thies; Angela Dai; Matthias Niessner; | |
| 109 | Maximum Likelihood Training of Score-Based Diffusion Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that for a specific weighting scheme, the objective upper bounds the negative log-likelihood, thus enabling approximate maximum likelihood training of score-based diffusion models. |
Yang Song; Conor Durkan; Iain Murray; Stefano Ermon; | |
| 110 | Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the asymmetric low-rank factorization problem:\[\min_{\mathbf{U} \in \mathbb{R}^{m \times d}, \mathbf{V} \in \mathbb{R}^{n \times d}} \frac{1}{2}\|\mathbf{U}\mathbf{V}^\top -\mathbf{\Sigma}\|_F^2\]where $\mathbf{\Sigma}$ is a given matrix of size $m \times n$ and rank $d$. |
Tian Ye; Simon S. Du; | |
| 111 | Adaptive Data Augmentation on Temporal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information. |
Yiwei Wang; Yujun Cai; Yuxuan Liang; Henghui Ding; Changhu Wang; Siddharth Bhatia; Bryan Hooi; | |
| 112 | Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce regularized Frank-Wolfe, a general and effective algorithm for inference and learning of dense conditional random fields (CRFs). |
�.Khu� L�-Huu; Karteek Alahari; | |
| 113 | Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we propose Terra, an imperative-symbolic co-execution system that can handle any imperative DL programs while achieving the optimized performance of symbolic graph execution. |
Taebum Kim; Eunji Jeong; Geon-Woo Kim; Yunmo Koo; Sehoon Kim; Gyeongin Yu; Byung-Gon Chun; | |
| 114 | Uniform Sampling Over Episode Difficulty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on this method, we perform an extensive analysis and find that sampling uniformly over episode difficulty outperforms other sampling schemes, including curriculum and easy-/hard-mining. |
S�bastien Arnold; Guneet Dhillon; Avinash Ravichandran; Stefano Soatto; | |
| 115 | Scalable Intervention Target Estimation in Linear Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a scalable and efficient algorithm that consistently identifies all intervention targets. |
Burak Varici; Karthikeyan Shanmugam; Prasanna Sattigeri; Ali Tajer; | code |
| 116 | Play to Grade: Testing Coding Games As Classifying Markov Decision Process Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we formalize the challenge of providing feedback to interactive programs as a task of classifying Markov Decision Processes (MDPs). |
Allen Nie; Emma Brunskill; Chris Piech; | |
| 117 | Distributional Reinforcement Learning for Multi-Dimensional Reward Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fully inherit the benefits of distributional RL and hybrid reward architectures, we introduce Multi-Dimensional Distributional DQN (MD3QN), which extends distributional RL to model the joint return distribution from multiple reward sources. |
Pushi Zhang; Xiaoyu Chen; Li Zhao; Wei Xiong; Tao Qin; Tie-Yan Liu; | |
| 118 | Differentiable Unsupervised Feature Selection Based on A Gated Laplacian Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a method for unsupervised feature selection, and we demonstrate its advantage in clustering, a common unsupervised task. |
Ofir Lindenbaum; Uri Shaham; Erez Peterfreund; Jonathan Svirsky; Nicolas Casey; Yuval Kluger; | |
| 119 | Smooth Bilevel Programming for Sparse Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how a surprisingly simple re-parametrization of IRLS, coupled with a bilevel resolution (instead of an alternating scheme) is able to achieve top performances on a wide range of sparsity (such as Lasso, group Lasso and trace norm regularizations), regularization strength (including hard constraints), and design matrices (ranging from correlated designs to differential operators). |
Clarice Poon; Gabriel Peyr�; | |
| 120 | Grounding Representation Similarity Through Statistical Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: These disagreements raise the question: which, if any, of these dissimilarity measures should we believe? We provide a framework to ground this question through a concrete test: measures should have \emph{sensitivity} to changes that affect functional behavior, and \emph{specificity} against changes that do not. |
Frances Ding; Jean-Stanislas Denain; Jacob Steinhardt; | |
| 121 | A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. |
Mingde Zhao; Zhen Liu; Sitao Luan; Shuyuan Zhang; Doina Precup; Yoshua Bengio; | |
| 122 | Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new provably efficient algorithm, called UCRL-RFE under the Linear Mixture MDP assumption, where the transition probability kernel of the MDP can be parameterized by a linear function over certain feature mappings defined on the triplet of state, action, and next state. |
Weitong ZHANG; Dongruo Zhou; Quanquan Gu; | |
| 123 | Beltrami Flow and Neural Diffusion on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel class of graph neural networks based on the discretized Beltrami flow, a non-Euclidean diffusion PDE. |
Benjamin Chamberlain; James Rowbottom; Davide Eynard; Francesco Di Giovanni; Xiaowen Dong; Michael Bronstein; | |
| 124 | Think Big, Teach Small: Do Language Models Distil Occam’s Razor? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We frame this question as a teaching problem with strong priors, and study whether language models can identify simple algorithmic concepts from small witness sets. |
Gonzalo Jaimovitch-Lopez; David Castellano Falc�n; Cesar Ferri; Jos� Hern�ndez-Orallo; | |
| 125 | Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). |
Hermanni H�lv�; Sylvain Le Corff; Luc Leh�ricy; Jonathan So; Yongjie Zhu; Elisabeth Gassiat; Aapo Hyvarinen; | |
| 126 | Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We generalize the idea of conditional parameterization — using trainable functions of input parameters to generate the weights of a neural network, and extend them in a flexible way to encode critical information. |
Jiayang Xu; Aniruddhe Pradhan; Karthikeyan Duraisamy; | |
| 127 | USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For learning foundations, we present learning-error analysis under the PAC-Bayesian framework using a new margin-based analysis. |
Guangmo Tong; | |
| 128 | Adaptive Conformal Inference Under Distribution Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop methods for forming prediction sets in an online setting where the data generating distribution is allowed to vary over time in an unknown fashion. |
Isaac Gibbs; Emmanuel Candes; | |
| 129 | Periodic Activation Functions Induce Stationarity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We seek to build models that `know what they do not know’ by introducing inductive biases in the function space. |
Lassi Meronen; Martin Trapp; Arno Solin; | |
| 130 | Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we build on top of recent advances in domain-adaptation theory, and from this perspective, propose ways to minimize the reality gap. |
David Acuna; Jonah Philion; Sanja Fidler; | |
| 131 | KS-GNN: Keywords Search Over Incomplete Graphs Via Graphs Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the problem of keyword search over incomplete graphs, we propose a novel model named KS-GNN based on the graph neural network and the auto-encoder. |
YU HAO; Xin Cao; Yufan Sheng; Yixiang Fang; Wei Wang; | |
| 132 | Reconstruction for Powerful Graph Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show the extent to which graph reconstruction—reconstructing a graph from its subgraphs—can mitigate the theoretical and practical problems currently faced by GRL architectures. |
Leonardo Cotta; Christopher Morris; Bruno Ribeiro; | |
| 133 | Revealing and Protecting Labels in Distributed Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a method to discover the set of labels of training samples from only the gradient of the last layer and the id to label mapping. |
Trung Dang; Om Thakkar; Swaroop Ramaswamy; Rajiv Mathews; Peter Chin; Fran�oise Beaufays; | |
| 134 | Solving Graph-based Public Goods Games with Tree Search and Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we adopt the perspective of a central planner with a global view of a network of self-interested agents and the goal of maximizing some desired property in the context of a best-shot public goods game. |
Victor-Alexandru Darvariu; Stephen Hailes; Mirco Musolesi; | |
| 135 | Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a principled technical method to optimize AUPRC for deep learning. |
Qi Qi; Youzhi Luo; Zhao Xu; Shuiwang Ji; Tianbao Yang; | code |
| 136 | Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we establish a theoretically grounded and practically useful framework for the transfer learning of GNNs. |
Qi Zhu; Carl Yang; Yidan Xu; Haonan Wang; Chao Zhang; Jiawei Han; | |
| 137 | You Are Caught Stealing My Winning Lottery Ticket! Making A Lottery Ticket Claim Its Ownership Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our setting adds a new dimension to the recently soaring interest in protecting against the intellectual property (IP) infringement of deep models and verifying their ownerships, since they take owners’ massive/unique resources to develop or train. |
Xuxi Chen; Tianlong Chen; Zhenyu Zhang; Zhangyang Wang; | code |
| 138 | Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a first-order oracle complexity lower bound for finding stationary points of min-max optimization problems where the objective function is smooth, nonconvex in the minimization variable, and strongly concave in the maximization variable. |
Haochuan Li; Yi Tian; Jingzhao Zhang; Ali Jadbabaie; | |
| 139 | Early-stopped Neural Networks Are Consistent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is … |
Ziwei Ji; Justin Li; Matus Telgarsky; | |
| 140 | NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding Via ADMM Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such an issue in a principled manner, we introduce a new learning framework, called NxMTransformer, to induce NxM semi-structured sparsity on pretrained language models for natural language understanding to obtain better performance. |
Connor Holmes; Minjia Zhang; Yuxiong He; Bo Wu; | |
| 141 | Reliable Decisions with Threshold Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a stronger notion of calibration called threshold calibration, which is exactly the condition required to ensure that decision loss is predicted accurately for threshold decisions. |
Roshni Sahoo; Shengjia Zhao; Alyssa Chen; Stefano Ermon; | |
| 142 | End-to-End Weak Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these caveats we propose an end-to-end approach for directly learning the downstream model by maximizing its agreement with probabilistic labels generated by reparameterizing previous probabilistic posteriors with a neural network. |
Salva R�hling Cachay; Benedikt Boecking; Artur Dubrawski; | code |
| 143 | Shift Invariance Can Reduce Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background. |
Vasu Singla; Songwei Ge; Basri Ronen; David Jacobs; | |
| 144 | Wisdom of The Crowd Voting: Truthful Aggregation of Voter Information and Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider two-alternative elections where voters’ preferences depend on a state variable that is not directly observable. |
Grant Schoenebeck; Biaoshuai Tao; | |
| 145 | Replay-Guided Adversarial Environment Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we cast Prioritized Level Replay (PLR), an empirically successful but theoretically unmotivated method that selectively samples randomly-generated training levels, as UED. We argue that by curating completely random levels, PLR, too, can generate novel and complex levels for effective training. |
Minqi Jiang; Michael Dennis; Jack Parker-Holder; Jakob Foerster; Edward Grefenstette; Tim Rockt�schel; | |
| 146 | There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). |
Nathan Grinsztajn; Johan Ferret; Olivier Pietquin; philippe preux; Matthieu Geist; | |
| 147 | Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work, we investigate how both approaches can be integrated into one framework that combines their strengths. |
Ingmar Schubert; Danny Driess; Ozgur Oguz; Marc Toussaint; | |
| 148 | Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote diversity in sample generation without degrading the overall quality, we propose a simple yet effective method to diagnose and emphasize underrepresented samples during training of a GAN. |
Jinhee Lee; Haeri Kim; Youngkyu Hong; Hye Won Chung; | |
| 149 | Online Multi-Armed Bandits with Adaptive Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our thesis in this paper is that more sophisticated inference schemes that take into account the adaptive nature of the sequentially collected data can unlock further performance gains, even though both UCB and TS type algorithms are optimal in the worst case. |
Maria Dimakopoulou; Zhimei Ren; Zhengyuan Zhou; | |
| 150 | Efficient Truncated Linear Regression with Unknown Noise Variance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the first computationally and statistically efficient estimators for truncated linear regression when the noise variance is unknown, estimating both the linear model and the variance of the noise. |
Constantinos Daskalakis; Patroklos Stefanou; Rui Yao; Emmanouil Zampetakis; | |
| 151 | Breaking The Dilemma of Medical Image-to-image Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to break the dilemma of the existing modes, we propose a new unsupervised mode called RegGAN for medical image-to-image translation. |
Lingke Kong; Chenyu Lian; Detian Huang; zhenjiang li; Yanle Hu; Qichao Zhou; | code |
| 152 | Temporally Abstract Partial Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we define a notion of affordances for options, and develop temporally abstract partial option models, that take into account the fact that an option might be affordable only in certain situations. |
Khimya Khetarpal; Zafarali Ahmed; Gheorghe Comanici; Doina Precup; | |
| 153 | TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, we propose a new simplified decoder, which drops the full attention implementation with the softmax weighting, keeping only the query-key similarity computation. |
Shengcai Liao; Ling Shao; | code |
| 154 | Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We build on traditional SPI algorithms and propose a novel method based on Safe Policy Iteration with Baseline Bootstrapping (SPIBB, Laroche et al., 2019) that provides high probability guarantees on the performance of the agent in the true environment. |
harsh satija; Philip S. Thomas; Joelle Pineau; Romain Laroche; | |
| 155 | Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Automated evaluations declare a winning model when corresponding human evaluations do not, calling into question the validity of fully automatic evaluations independent of human judgments. |
Alexander Hoyle; Pranav Goel; Andrew Hian-Cheong; Denis Peskov; Jordan Boyd-Graber; Philip Resnik; | |
| 156 | INDIGO: GNN-Based Inductive Knowledge Graph Completion Using Pair-Wise Encoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach, where the KG is fully encoded into a GNN in a transparent way, and where the predicted triples can be read out directly from the last layer of the GNN without the need for additional components or scoring functions. |
Shuwen Liu; Bernardo Grau; Ian Horrocks; Egor Kostylev; | |
| 157 | Do Input Gradients Highlight Discriminative Features? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Post-hoc gradient-based interpretability methods [Simonyan et al., 2013, Smilkov et al., 2017] that provide instance-specific explanations of model predictions are often based on assumption (A): magnitude of input gradients-gradients of logits with respect to input-noisily highlight discriminative task-relevant features. In this work, we test the validity of assumption (A) using a three-pronged approach: |
Harshay Shah; Prateek Jain; Praneeth Netrapalli; | |
| 158 | Improving Conditional Coverage Via Orthogonal Quantile Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a method to generate prediction intervals that have a user-specified coverage level across all regions of feature-space, a property called conditional coverage. |
Shai Feldman; Stephen Bates; Yaniv Romano; | |
| 159 | Minimizing Polarization and Disagreement in Social Networks Via Link Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple greedy algorithm with a constant-factor approximation that solves the problem in cubic running time, and we provide theoretical analysis of the approximation guarantee for the algorithm. |
Liwang Zhu; Qi Bao; Zhongzhi Zhang; | |
| 160 | Adversarial Attacks on Black Box Video Classifiers: Leveraging The Power of Geometric Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that such effective gradients can be searched for by parameterizing the temporal structure of the search space with geometric transformations. |
Shasha Li; Abhishek Aich; Shitong Zhu; Salman Asif; Chengyu Song; Amit Roy-Chowdhury; Srikanth Krishnamurthy; | |
| 161 | Optimal Rates for Random Order Online Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Focusing on the scenario where the cumulative loss function is (strongly) convex, yet individual loss functions are smooth but might be non-convex, we give algorithms that achieve the optimal bounds and significantly outperform the results of Garber et al. (2020), completely removing the dimension dependence and improve their scaling with respect to the strong convexity parameter. |
Uri Sherman; Tomer Koren; Yishay Mansour; | |
| 162 | Discrete-Valued Neural Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we further tighten the bottleneck via discreteness of the representations transmitted between components. |
Dianbo Liu; Alex M. Lamb; Kenji Kawaguchi; Anirudh Goyal ALIAS PARTH GOYAL; Chen Sun; Michael C. Mozer; Yoshua Bengio; | |
| 163 | Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage the computation methods for kernel machines to alleviate the high computational cost and introduce Skyformer, which replaces the softmax structure with a Gaussian kernel to stabilize the model training and adapts the Nyström method to a non-positive semidefinite matrix to accelerate the computation. |
Yifan Chen; Qi Zeng; Heng Ji; Yun Yang; | |
| 164 | TransMIL: Transformer Based Correlated Multiple Instance Learning for Whole Slide Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence. |
Zhuchen Shao; Hao Bian; Yang Chen; Yifeng Wang; Jian Zhang; Xiangyang Ji; yongbing zhang; | code |
| 165 | Multi-view Contrastive Graph Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generic framework to cluster multi-view attributed graph data. |
ErLin Pan; Zhao Kang; | |
| 166 | Inverse-Weighted Survival Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve this dilemma, we introduce Inverse-Weighted Survival Games to train both failure and censoring models with respect to criteria such as BS or BLL. |
Xintian Han; Mark Goldstein; Aahlad Puli; Thomas Wies; Adler Perotte; Rajesh Ranganath; | |
| 167 | Generalization Bounds for Meta-Learning Via PAC-Bayes and Uniform Stability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive a probably approximately correct (PAC) bound for gradient-based meta-learning using two different generalization frameworks in order to deal with the qualitatively different challenges of generalization at the base and meta levels. |
Alec Farid; Anirudha Majumdar; | |
| 168 | Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel acquisition function, NEHVI, that overcomes this important practical limitation by applying a Bayesian treatment to the popular expected hypervolume improvement (EHVI) criterion and integrating over this uncertainty in the Pareto frontier. |
Samuel Daulton; Maximilian Balandat; Eytan Bakshy; | |
| 169 | Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots. |
Jagdeep Bhatia; Holly Jackson; Yunsheng Tian; Jie Xu; Wojciech Matusik; | code |
| 170 | On Calibration and Out-of-Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we draw a link between OOD performance and model calibration, arguing that calibration across multiple domains can be viewed as a special case of an invariant representation leading to better OOD generalization. |
Yoav Wald; Amir Feder; Daniel Greenfeld; Uri Shalit; | |
| 171 | On The Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a simple gradient truncation mechanism is proposed to address this issue. |
Junyu Zhang; Chengzhuo Ni; zheng Yu; Csaba Szepesvari; Mengdi Wang; | |
| 172 | Circa: Stochastic ReLUs for Private Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we re-think ReLU computations and propose optimizations for PI tailored to properties of neural networks. |
Zahra Ghodsi; Nandan Kumar Jha; Brandon Reagen; Siddharth Garg; | |
| 173 | Reinforcement Learning in Reward-Mixing MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP). |
Jeongyeol Kwon; Yonathan Efroni; Constantine Caramanis; Shie Mannor; | |
| 174 | A Gang of Adversarial Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two learning algorithms, GABA-I and GABA-II, which exploit the network structure to bias towards functions of low $\Psi$ values. |
Mark Herbster; Stephen Pasteris; Fabio Vitale; Massimiliano Pontil; | |
| 175 | Explaining Hyperparameter Optimization Via Partial Dependence Plots Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging the posterior uncertainty of the BO surrogate model, we introduce a variant of the PDP with estimated confidence bands.We propose to partition the hyperparameter space to obtain more confident and reliable PDPs in relevant sub-regions. |
Julia Moosbauer; Julia Herbinger; Giuseppe Casalicchio; Marius Lindauer; Bernd Bischl; | |
| 176 | Robustifying Algorithms of Learning Latent Trees with Vector Variables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider learning the structures of Gaussian latent tree models with vector observations when a subset of them are arbitrarily corrupted. |
Fengzhuo Zhang; Vincent Tan; | |
| 177 | Representation Learning on Spatial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, this paper proposes a generic framework for spatial network representation learning. |
Zheng Zhang; Liang Zhao; | code |
| 178 | Continuous-time Edge Modelling Using Non-parametric Point Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we discuss various approaches to model design, and develop three variants of non-parametric point processes for continuous-time edge modelling (CTEM). |
Xuhui Fan; Bin Li; Feng Zhou; Scott SIsson; | |
| 179 | Deep Inference of Latent Dynamics with Spatio-temporal Super-resolution Using Selective Backpropagation Through Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. |
Feng Zhu; Andrew Sedler; Harrison Grier; Nauman Ahad; Mark Davenport; Matthew Kaufman; Andrea Giovannucci; Chethan Pandarinath; | |
| 180 | Memory-efficient Patch-based Inference for Tiny Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this issue, we propose a generic patch-by-patch inference scheduling, which operates only on a small spatial region of the feature map and significantly cuts down the peak memory. |
Ji Lin; Wei-Ming Chen; Han Cai; Chuang Gan; Song Han; | |
| 181 | Self-Interpretable Model with Transformation Equivariant Interpretation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose to learn robust interpretation through transformation equivariant regularization in a self-interpretable model. |
Yipei Wang; Xiaoqian Wang; | |
| 182 | Solving Min-Max Optimization with Hidden Structure Via Gradient Descent Ascent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide conditions under which vanilla GDA provably converges not merely to local Nash, but the actual von-Neumann solution. |
Emmanouil-Vasileios Vlatakis-Gkaragkounis; Lampros Flokas; Georgios Piliouras; | |
| 183 | Preserved Central Model for Faster Bidirectional Compression in Distributed Settings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose and analyze a new algorithm that performs bidirectional compression and achieves the same convergence rate as algorithms using only uplink (from the local workers to the central server) compression. |
Constantin Philippenko; Aymeric Dieuleveut; | |
| 184 | Understanding Instance-based Interpretability of Variational Auto-Encoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate influence functions [20], a popular instance-based interpretation method, for a class of deep generative models called variational auto-encoders (VAE). |
Zhifeng Kong; Kamalika Chaudhuri; | |
| 185 | Voxel-based 3D Detection and Reconstruction of Multiple Objects from A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to learn a regular grid of 3D voxel features from the input image which is aligned with 3D scene space via a 3D feature lifting operator. |
Feng Liu; Xiaoming Liu; | |
| 186 | Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new algorithm for domain generalization (DG), \textit{test-time template adjuster (T3A)}, aiming to robustify a model to unknown distribution shift. |
Yusuke Iwasawa; Yutaka Matsuo; | |
| 187 | Luna: Linear Unified Nested Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Luna, a linear unified nested attention mechanism that approximates softmax attention with two nested linear attention functions, yielding only linear (as opposed to quadratic) time and space complexity. |
Xuezhe Ma; Xiang Kong; Sinong Wang; Chunting Zhou; Jonathan May; Hao Ma; Luke Zettlemoyer; | |
| 188 | Iterative Causal Discovery in The Possible Presence of Latent Confounders and Selection Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a sound and complete algorithm, called iterative causal discovery (ICD), for recovering causal graphs in the presence of latent confounders and selection bias. |
Raanan Yehezkel Rohekar; Shami Nisimov; Yaniv Gurwicz; Gal Novik; | |
| 189 | Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a formulation of hindsight relabelling for meta-RL, which relabels experience during meta-training to enable learning to learn entirely using sparse reward. |
Charles Packer; Pieter Abbeel; Joseph E. Gonzalez; | |
| 190 | A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Bayesian-symbolic framework (BSP) for physical reasoning and learning that is close to human-level sample-efficiency and accuracy. |
Kai Xu; Akash Srivastava; Dan Gutfreund; Felix Sosa; Tomer Ullman; Josh Tenenbaum; Charles Sutton; | |
| 191 | Associating Objects with Transformers for Video Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the problem, we propose an Associating Objects with Transformers (AOT) approach to match and decode multiple objects uniformly. |
Zongxin Yang; Yunchao Wei; Yi Yang; | |
| 192 | Automatic Symmetry Discovery with Lie Algebra Convolutional Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to work with Lie algebras (infinitesimal generators) instead of Lie groups. |
Nima Dehmamy; Robin Walters; Yanchen Liu; Dashun Wang; Rose Yu; | |
| 193 | Zero Time Waste: Recycling Predictions in Early Exit Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this issue, we introduce Zero Time Waste (ZTW), a novel approach in which each IC reuses predictions returned by its predecessors by (1) adding direct connections between ICs and (2) combining previous outputs in an ensemble-like manner. |
Maciej Wolczyk; Bartosz W�jcik; Klaudia Balazy; Igor Podolak; Jacek Tabor; Marek Smieja; Tomasz Trzcinski; | |
| 194 | On Model Calibration for Long-Tailed Object Detection and Instance Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate a largely overlooked approach — post-processing calibration of confidence scores. |
Tai-Yu Pan; Cheng Zhang; Yandong Li; Hexiang Hu; Dong Xuan; Soravit Changpinyo; Boqing Gong; Wei-Lun Chao; | code |
| 195 | ReSSL: Relational Self-Supervised Learning with Weak Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduced a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. |
Mingkai Zheng; Shan You; Fei Wang; Chen Qian; Changshui Zhang; Xiaogang Wang; Chang Xu; | |
| 196 | Learning to See By Looking at Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we go a step further and ask if we can do away with real image datasets entirely, instead learning from procedural noise processes. |
Manel Baradad; Jonas Wulff; Tongzhou Wang; Phillip Isola; Antonio Torralba; | |
| 197 | Explicit Loss Asymptotics in The Gradient Descent Training of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work we take a different approach and show that the learning trajectory of a wide network in a lazy training regime can be characterized by an explicit asymptotic at large training times. |
Maksim Velikanov; Dmitry Yarotsky; | |
| 198 | Test-Time Personalization with A Transformer for Human Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to personalize a 2D human pose estimator given a set of test images of a person without using any manual annotations. |
Yizhuo Li; Miao Hao; Zonglin Di; Nitesh Bharadwaj Gundavarapu; Xiaolong Wang; | code |
| 199 | Towards Scalable Unpaired Virtual Try-On Via Patch-Routed Spatially-Adaptive GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To achieve a scalable virtual try-on system that can transfer arbitrary garments between a source and a target person in an unsupervised manner, we thus propose a texture-preserving end-to-end network, the PAtch-routed SpaTially-Adaptive GAN (PASTA-GAN), that facilitates real-world unpaired virtual try-on. |
Zhenyu Xie; Zaiyu Huang; Fuwei Zhao; Haoye Dong; Michael Kampffmeyer; Xiaodan Liang; | |
| 200 | Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we conduct an in-depth analysis of GPT-2, which is the most downloaded text generation model on HuggingFace, with over half a million downloads per month. |
Hannah Rose Kirk; yennie jun; Filippo Volpin; Haider Iqbal; Elias Benussi; Frederic Dreyer; Aleksandar Shtedritski; Yuki Asano; | |
| 201 | Weisfeiler and Lehman Go Cellular: CW Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend recent theoretical results on SCs to regular Cell Complexes, topological objects that flexibly subsume SCs and graphs. |
Cristian Bodnar; Fabrizio Frasca; Nina Otter; Yu Guang Wang; Pietro Li�; Guido F. Montufar; Michael Bronstein; | |
| 202 | Learning Conjoint Attentions for Graph Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). |
Tiantian He; Yew Ong; L Bai; | |
| 203 | Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study aims to develop bandit algorithms that automatically exploit tendencies of certain environments to improve performance, without any prior knowledge regarding the environments. |
Shinji Ito; | |
| 204 | Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we find that non-selective attention sharing is sub-optimal for achieving good generalization across all languages and domains. |
Hongyu Gong; Yun Tang; Juan Pino; Xian Li; | |
| 205 | Cardinality-Regularized Hawkes-Granger Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new sparse Granger-causal learning framework for temporal event data. |
Tsuyoshi Ide; Georgios Kollias; Dzung Phan; Naoki Abe; | |
| 206 | Aligned Structured Sparsity Learning for Efficient Image Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above issues, we propose aligned structured sparsity learning (ASSL), which introduces a weight normalization layer and applies $L_2$ regularization to the scale parameters for sparsity. |
Yulun Zhang; Huan Wang; Can Qin; Yun Fu; | |
| 207 | Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To the best of our knowledge, our work, for the first time, characterizes the performance of training a pruned neural network by analyzing the geometric structure of the objective function and the sample complexity to achieve zero generalization error. |
Shuai Zhang; Meng Wang; Sijia Liu; Pin-Yu Chen; Jinjun Xiong; | |
| 208 | Constrained Robust Submodular Partitioning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two classes of algorithms, i.e., Min-Block Greedy based algorithms (with an $\Omega(1/m)$ bound), and Round-Robin Greedy based algorithms (with a constant bound) and show that under various constraints, they still have good approximation guarantees. |
Shengjie Wang; Tianyi Zhou; Chandrashekhar Lavania; Jeff A. Bilmes; | |
| 209 | Online Knapsack with Frequency Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we continue this line of work by studying the online knapsack problem, but with very weak predictions: in the form of knowing an upper and lower bound for the number of items of each value. |
Sungjin Im; Ravi Kumar; Mahshid Montazer Qaem; Manish Purohit; | |
| 210 | On Component Interactions in Two-Stage Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As manual search for a good pool allocation is difficult, we propose to learn one instead using a Mixture-of-Experts based approach. |
Jiri Hron; Karl Krauth; Michael Jordan; Niki Kilbertus; | |
| 211 | Lip to Speech Synthesis with Visual Context Attentional GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel lip-to-speech generative adversarial network, Visual Context Attentional GAN (VCA-GAN), which can jointly model local and global lip movements during speech synthesis. |
Minsu Kim; Joanna Hong; Yong Man Ro; | |
| 212 | Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we bridge the gap by studying DRO algorithms for general smooth non-convex losses. |
Jikai Jin; Bohang Zhang; Haiyang Wang; Liwei Wang; | |
| 213 | Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose goal-aware cross-entropy (GACE) loss, that can be utilized in a self-supervised way using auto-labeled goal states alongside reinforcement learning. |
Kibeom Kim; Min Whoo Lee; Yoonsung Kim; JeHwan Ryu; Minsu Lee; Byoung-Tak Zhang; | |
| 214 | Smooth Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a class of smooth mixture transformations working on both compact intervals and hypertori.Mixture transformations employ root-finding methods to invert them in practice, which has so far prevented bi-directional flow training. |
Jonas K�hler; Andreas Kr�mer; Frank Noe; | |
| 215 | MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to create generalizable and controllable neural signed distance fields (SDFs) that represent clothed humans from monocular depth observations. |
Shaofei Wang; Marko Mihajlovic; Qianli Ma; Andreas Geiger; Siyu Tang; | |
| 216 | Distributed Principal Component Analysis with Limited Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new quantized variant of Riemannian gradient descent to solve this problem, and prove that the algorithm converges with high probability under a set of necessary spherical-convexity properties. |
Foivos Alimisis; Peter Davies; Bart Vandereycken; Dan Alistarh; | |
| 217 | Newton-LESS: Sparsification Without Trade-offs for The Sketched Newton Update Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove that Newton-LESS enjoys nearly the same problem-independent local convergence rate as Gaussian embeddings for a large class of functions. In particular, this leads to a new state-of-the-art convergence result for an iterative least squares solver. |
Michal Derezinski; Jonathan Lacotte; Mert Pilanci; Michael W. Mahoney; | |
| 218 | Confident Anchor-Induced Multi-Source Free Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we develop a novel Confident-Anchor-induced multi-source-free Domain Adaptation (CAiDA) model, which is a pioneer exploration of knowledge adaptation from multiple source domains to the unlabeled target domain without any source data, but with only pre-trained source models. |
Jiahua Dong; Zhen Fang; Anjin Liu; Gan Sun; Tongliang Liu; | code |
| 219 | Word2Fun: Modelling Words As Functions for Diachronic Word Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we will carry on this line of work by learning explicit functions over time for each word. |
benyou wang; Emanuele Di Buccio; Massimo Melucci; | code |
| 220 | Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we prove that a variant of IRLS converges \emph{with a global linear rate} to a sparse solution, i.e., with a linear error decrease occurring immediately from any initialization if the measurements fulfill the usual null space property assumption. |
Christian K�mmerle; Claudio Mayrink Verdun; Dominik St�ger; | |
| 221 | Low-Rank Constraints for Fast Inference in Structured Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. |
Justin Chiu; Yuntian Deng; Alexander Rush; | |
| 222 | Accumulative Poisoning Attacks on Real-time Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the real-time settings and propose a new attacking strategy, which affiliates an accumulative phase with poisoning attacks to secretly (i.e., without affecting accuracy) magnify the destructive effect of a (poisoned) trigger batch. |
Tianyu Pang; Xiao Yang; Yinpeng Dong; Hang Su; Jun Zhu; | |
| 223 | UCB-based Algorithms for Multinomial Logistic Regression Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this problem, we present MNL-UCB, an upper confidence bound (UCB)-based algorithm, that achieves regret $\tilde{\mathcal{O}}(dK\sqrt{T})$ with small dependency on problem-dependent constants that can otherwise be arbitrarily large and lead to loose regret bounds. |
Sanae Amani; Christos Thrampoulidis; | |
| 224 | Estimating The Long-Term Effects of Novel Treatments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a surrogate-based approach using a long-term dataset where only past treatments were administered and a short-term dataset where novel treatments have been administered. |
Keith Battocchi; Eleanor Dillon; Maggie Hei; Greg Lewis; Miruna Oprescu; Vasilis Syrgkanis; | |
| 225 | Dual Progressive Prototype Network for Generalized Zero-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we handle the critical issue of domain shift problem, i.e., confusion between seen and unseen categories, by progressively improving cross-domain transferability and category discriminability of visual representations. |
Chaoqun Wang; Shaobo Min; Xuejin Chen; Xiaoyan Sun; Houqiang Li; | |
| 226 | Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We make a step toward addressing this open problem, by providing the first sample complexity results for policy gradient (PG) methods in two fundamental risk-sensitive/robust control settings: the linear exponential quadratic Gaussian, and the linear-quadratic (LQ) disturbance attenuation problems. |
Kaiqing Zhang; Xiangyuan Zhang; Bin Hu; Tamer Basar; | |
| 227 | G-PATE: Scalable Differentially Private Data Generator Via Private Aggregation of Teacher Discriminators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel privacy-preserving data Generative model based on the PATE framework (G-PATE), aiming to train a scalable differentially private data generator that preserves high generated data utility. |
Yunhui Long; Boxin Wang; Zhuolin Yang; Bhavya Kailkhura; Aston Zhang; Carl Gunter; Bo Li; | code |
| 228 | On The Existence of The Adversarial Bayes Classifier Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study a fundamental question regarding Bayes optimality for adversarial robustness. |
Pranjal Awasthi; Natalie Frank; Mehryar Mohri; | |
| 229 | Convex-Concave Min-Max Stackelberg Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce two first-order methods that solve a large class of convex-concave min-max Stackelberg games, and show that our methods converge in polynomial time. |
Denizalp Goktas; Amy Greenwald; | |
| 230 | Misspecified Gaussian Process Bandit Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we present two algorithms based on Gaussian process (GP) methods: an optimistic EC-GP-UCB algorithm that requires knowing the misspecification error, and Phased GP Uncertainty Sampling, an elimination-type algorithm that can adapt to unknown model misspecification. |
Ilija Bogunovic; Andreas Krause; | |
| 231 | Visual Adversarial Imitation Learning Using Variational Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This setting presents a number of challenges including representation learning for visual observations, sample complexity due to high dimensional spaces, and learning instability due to the lack of a fixed reward or learning signal. Towards addressing these challenges, we develop a variational model-based adversarial imitation learning (V-MAIL) algorithm. |
Rafael Rafailov; Tianhe Yu; Aravind Rajeswaran; Chelsea Finn; | code |
| 232 | Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents Object-aware REgularizatiOn (OREO), a simple technique that regularizes an imitation policy in an object-aware manner. |
Jongjin Park; Younggyo Seo; Chang Liu; Li Zhao; Tao Qin; Jinwoo Shin; Tie-Yan Liu; | |
| 233 | Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the feasibility of using state-of-the-art out-of-distribution detectors for reliable and trustworthy diagnostic predictions. |
Chunjong Park; Anas Awadalla; Tadayoshi Kohno; Shwetak Patel; | |
| 234 | Multiclass Boosting and The Cost of Weak Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study multiclass boosting with a possibly large number of classes or categories. |
Nataly Brukhim; Elad Hazan; Shay Moran; Indraneel Mukherjee; Robert E. Schapire; | |
| 235 | Partition-Based Formulations for Mixed-Integer Optimization of Trained ReLU Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a class of mixed-integer formulations for trained ReLU neural networks. |
Calvin Tsay; Nikos Vlassis; Alexander Thebelt; Ruth Misener; | |
| 236 | Hyperparameter Optimization Is Deceiving Us, and How to Stop It Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We call this process epistemic hyperparameter optimization (EHPO), and put forth a logical framework to capture its semantics and how it can lead to inconsistent conclusions about performance. |
A. Feder Cooper; Yucheng Lu; Jessica Forde; Christopher M. De Sa; | |
| 237 | On The Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this formulation, we propose a variant of the MAML method, named Stochastic Gradient Meta-Reinforcement Learning (SG-MRL), and study its convergence properties. |
Alireza Fallah; Kristian Georgiev; Aryan Mokhtari; Asuman Ozdaglar; | |
| 238 | 3D Pose Transfer with Correspondence Learning and Mesh Refinement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a correspondence-refinement network to help the 3D pose transfer for both human and animal meshes. |
Chaoyue Song; Jiacheng Wei; Ruibo Li; Fayao Liu; Guosheng Lin; | |
| 239 | Framing RNN As A Kernel Method: A Neural ODE Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a RNN can be viewed as a linear function of a specific feature set of the input sequence, known as the signature. |
Adeline Fermanian; Pierre Marion; Jean-Philippe Vert; G�rard Biau; | |
| 240 | Contextual Similarity Aggregation with Self-attention for Visual Re-ranking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this observation, in this paper, we propose a visual re-ranking method by contextual similarity aggregation with self-attention. |
Jianbo Ouyang; Hui Wu; Min Wang; Wengang Zhou; Houqiang Li; | |
| 241 | Can Information Flows Suggest Targets for Interventions in Neural Circuits? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by neuroscientific and clinical applications, we empirically examine whether observational measures of information flow can suggest interventions. |
Praveen Venkatesh; Sanghamitra Dutta; Neil Mehta; Pulkit Grover; | |
| 242 | AutoBalance: Optimized Loss Functions for Imbalanced Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose AutoBalance, a bi-level optimization framework that automatically designs a training loss function to optimize a blend of accuracy and fairness-seeking objectives. |
Mingchen Li; Xuechen Zhang; Christos Thrampoulidis; Jiasi Chen; Samet Oymak; | |
| 243 | SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge the gap, this paper develops a new method, SyncTwin, that learns a patient-specific time-constant representation from the pre-treatment observations. |
Zhaozhi Qian; Yao Zhang; Ioana Bica; Angela Wood; Mihaela van der Schaar; | |
| 244 | Statistical Query Lower Bounds for List-Decodable Linear Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of list-decodable linear regression, where an adversary can corrupt a majority of the examples. |
Ilias Diakonikolas; Daniel Kane; Ankit Pensia; Thanasis Pittas; Alistair Stewart; | |
| 245 | Unsupervised Motion Representation Learning with Capsule Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. |
Ziwei Xu; Xudong Shen; Yongkang Wong; Mohan S. Kankanhalli; | |
| 246 | VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we propose a coordination detection framework incorporating neural temporal point process with prior knowledge such as temporal logic or pre-defined filtering functions. |
Yizhou Zhang; Karishma Sharma; Yan Liu; | |
| 247 | An Improved Analysis and Rates for Variance Reduction Under Without-replacement Sampling Orders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we will improve the convergence analysis and rates of variance reduction under without-replacement sampling orders for composite finite-sum minimization.Our results are in two-folds. |
Xinmeng Huang; Kun Yuan; Xianghui Mao; Wotao Yin; | |
| 248 | Exploring Forensic Dental Identification with Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we pioneer to study deep learning for dental forensic identification based on panoramic radiographs. |
Yuan Liang; Weikun Han; Liang Qiu; Chen Wu; Yiting Shao; Kun Wang; Lei He; | code |
| 249 | Learning to Generate Realistic Noisy Images Via Pixel-level Noise-aware Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, this work investigates how to generate realistic noisy images. |
Yuanhao Cai; Xiaowan Hu; Haoqian Wang; Yulun Zhang; Hanspeter Pfister; Donglai Wei; | |
| 250 | Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a problem in power networks that creates an exciting and yet challenging real-world scenario for application of multi-agent reinforcement learning (MARL). |
Jianhong Wang; Wangkun Xu; Yunjie Gu; Wenbin Song; Tim Green; | |
| 251 | Looking Beyond Single Images for Contrastive Semantic Segmentation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach to contrastive representation learning for semantic segmentation. |
FEIHU ZHANG; Philip Torr; Rene Ranftl; Stephan Richter; | |
| 252 | A Constant Approximation Algorithm for Sequential Random-Order No-Substitution K-Median Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give the first algorithm for this setting that obtains a constant approximation factor on the optimal cost under a random arrival order, an exponential improvement over previous work. |
Tom Hess; Michal Moshkovitz; Sivan Sabato; | |
| 253 | Dangers of Bayesian Model Averaging Under Covariate Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explain this surprising result, showing how a Bayesian model average can in fact be problematic under covariate shift, particularly in cases where linear dependencies in the input features cause a lack of posterior contraction. |
Pavel Izmailov; Patrick Nicholson; Sanae Lotfi; Andrew G. Wilson; | |
| 254 | Learning Equilibria in Matching Markets from Bandit Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge this gap, we develop a framework and algorithms for learning stable market outcomes under uncertainty. |
Meena Jagadeesan; Alexander Wei; Yixin Wang; Michael Jordan; Jacob Steinhardt; | |
| 255 | Towards Lower Bounds on The Depth of ReLU Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We contribute to a better understanding of the class of functions that is represented by a neural network with ReLU activations and a given architecture. |
Christoph Hertrich; Amitabh Basu; Marco Di Summa; Martin Skutella; | |
| 256 | The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our analysis in this paper decouples capacity and width via the generalization of neural networks to Deep Gaussian Processes (Deep GP), a class of nonparametric hierarchical models that subsume neural nets. |
Geoff Pleiss; John P. Cunningham; | |
| 257 | Exact Marginal Prior Distributions of Finite Bayesian Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we derive exact solutions for the function space priors for individual input examples of a class of finite fully-connected feedforward Bayesian neural networks. |
Jacob Zavatone-Veth; Cengiz Pehlevan; | |
| 258 | Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce spatiotemporal joint filter decomposition to decouple spatial and temporal learning, while preserving spatiotemporal dependency in a video. |
Zichen Miao; Ze Wang; Xiuyuan Cheng; Qiang Qiu; | |
| 259 | Pooling By Sliced-Wasserstein Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a geometrically-interpretable and generic pooling mechanism for aggregating a set of features into a fixed-dimensional representation. |
Navid Naderializadeh; Joseph Comer; Reed Andrews; Heiko Hoffmann; Soheil Kolouri; | code |
| 260 | On The Theory of Reinforcement Learning with Once-per-Episode Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a theory of reinforcement learning (RL) in which the learner receives binary feedback only once at the end of an episode. |
Niladri Chatterji; Aldo Pacchiano; Peter Bartlett; Michael Jordan; | |
| 261 | ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To codify such a difference in nonlinearities and reveal a linear estimation property, we define ResNEsts, i.e., Residual Nonlinear Estimators, by simply dropping nonlinearities at the last residual representation from standard ResNets. We show that wide ResNEsts with bottleneck blocks can always guarantee a very desirable training property that standard ResNets aim to achieve, i.e., adding more blocks does not decrease performance given the same set of basis elements. |
Kuan-Lin Chen; Ching-Hua Lee; Harinath Garudadri; Bhaskar Rao; | |
| 262 | Locally Private Online Change Point Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our primary aim is to detect changes in the regression function $m_t(x)=\mathbb{E}(Y_t |X_t=x)$ as soon as the change occurs. |
Tom Berrett; Yi Yu; | |
| 263 | Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approach that incorporates both of these principles and demonstrate its effectiveness in several experiments. |
Kartik Ahuja; Ethan Caballero; Dinghuai Zhang; Jean-Christophe Gagnon-Audet; Yoshua Bengio; Ioannis Mitliagkas; Irina Rish; | |
| 264 | Repulsive Deep Ensembles Are Bayesian Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce a kernelized repulsive term in the update rule of the deep ensembles. |
Francesco D'Angelo; Vincent Fortuin; | |
| 265 | BayesIMP: Uncertainty Quantification for Causal Data Fusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the causal data fusion problem, where data arising from multiple causal graphs are combined to estimate the average treatment effect of a target variable. |
Siu Lun Chau; Jean-Francois Ton; Javier Gonz�lez; Yee Teh; Dino Sejdinovic; | |
| 266 | RMM: Reinforced Memory Management for Class-Incremental Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a dynamic memory management strategy that is optimized for the incremental phases and different object classes. |
Yaoyao Liu; Bernt Schiele; Qianru Sun; | code |
| 267 | Learning Compact Representations of Neural Networks Using DiscriminAtive Masking (DAM) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel single-stage structured pruning method termed DiscriminAtive Masking (DAM). |
Jie Bu; Arka Daw; M. Maruf; Anuj Karpatne; | code |
| 268 | Neural Auto-Curricula in Two-Player Zero-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel framework—Neural Auto-Curricula (NAC)—that leverages meta-gradient descent to automate the discovery of the learning update rule without explicit human design. |
Xidong Feng; Oliver Slumbers; Ziyu Wan; Bo Liu; Stephen McAleer; Ying Wen; Jun Wang; Yaodong Yang; | |
| 269 | ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a remedy we incorporate a coarse-to-fine hierarchy of context by combining the autoregressive formulation with a multinomial diffusion process: Whereas a multistage diffusion process successively compresses and removes information to coarsen an image, we train a Markov chain to invert this process. |
Patrick Esser; Robin Rombach; Andreas Blattmann; Bjorn Ommer; | |
| 270 | From Global to Local MDI Variable Importances for Random Forests and When They Are Shapley Values Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this context, we first show that the global Mean Decrease of Impurity (MDI) variable importance scores correspond to Shapley values under some conditions. Then, we derive a local MDI importance measure of variable relevance, which has a very natural connection with the global MDI measure and can be related to a new notion of local feature relevance. |
Antonio Sutera; Gilles Louppe; Van Anh Huynh-Thu; Louis Wehenkel; Pierre Geurts; | |
| 271 | Adversarial Robustness of Streaming Algorithms Through Importance Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce adversarially robust streaming algorithms for central machine learning and algorithmic tasks, such as regression and clustering, as well as their more general counterparts, subspace embedding, low-rank approximation, and coreset construction. |
Vladimir braverman; Avinatan Hasidim; Yossi Matias; Mariano Schain; Sandeep Silwal; Samson Zhou; | |
| 272 | Tractable Regularization of Probabilistic Circuits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we re-think regularization for PCs and propose two intuitive techniques, data softening and entropy regularization, that both take advantage of PCs’ tractability and still have an efficient implementation as a computation graph. |
Anji Liu; Guy Van den Broeck; | code |
| 273 | On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we develop a feature space for image transforms, and then use a new measure in this space between augmentations and corruptions called the Minimal Sample Distance to demonstrate there is a strong correlation between similarity and performance. |
Eric Mintun; Alexander Kirillov; Saining Xie; | code |
| 274 | Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple dynamic distillation-based approach to facilitate unlabeled images from the novel/base dataset. |
Ashraful Islam; Chun-Fu (Richard) Chen; Rameswar Panda; Leonid Karlinsky; Rogerio Feris; Richard Radke; | |
| 275 | Hypergraph Propagation and Community Selection for Objects Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these problems, we propose a novel hypergraph-based framework that efficiently propagates spatial information in query time and retrieves an object in the database accurately. |
Guoyuan An; Yuchi Huo; Sung-eui Yoon; | |
| 276 | Deep Learning Is Adaptive to Intrinsic Dimensionality of Model Smoothness in Anisotropic Besov Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand this property, we investigate the approximation and estimation ability of deep learning on {\it anisotropic Besov spaces}. |
Taiji Suzuki; Atsushi Nitanda; | |
| 277 | QuPeD: Quantized Personalization Via Distillation with Applications to Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a quantized and personalized FL algorithm QuPeD that facilitates collective (personalized model compression) training via knowledge distillation (KD) among clients who have access to heterogeneous data and resources. |
Kaan Ozkara; Navjot Singh; Deepesh Data; Suhas Diggavi; | |
| 278 | Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation Without Source Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA. |
Jiaxing Huang; Dayan Guan; Aoran Xiao; Shijian Lu; | |
| 279 | The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study several under-explored dimensions of FI explanations, providing conceptual and empirical improvements for this form of explanation. |
Peter Hase; Harry Xie; Mohit Bansal; | |
| 280 | Control Variates for Slate Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of off-policy evaluation from batched contextual bandit data with multidimensional actions, often termed slates. |
Nikos Vlassis; Ashok Chandrashekar; Fernando Amat; Nathan Kallus; | |
| 281 | Stabilizing Deep Q-Learning with ConvNets and Vision Transformers Under Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate causes of instability when using data augmentation in common off-policy RL algorithms. |
Nicklas Hansen; Hao Su; Xiaolong Wang; | |
| 282 | On Effective Scheduling of Model-based Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the analysis, we propose a framework named AutoMBPO to automatically schedule the real data ratio as well as other hyperparameters in training model-based policy optimization (MBPO) algorithm, a representative running case of model-based methods. |
Hang Lai; Jian Shen; Weinan Zhang; Yimin Huang; Xing Zhang; Ruiming Tang; Yong Yu; Zhenguo Li; | |
| 283 | Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While applications of these methods have been mostly limited to single-cell genomics, in this work, we develop a theoretical framework for domain adaptation in systems neuroscience. |
Dominic Gonschorek; Larissa H�fling; Klaudia Szatko; Katrin Franke; Timm Schubert; Benjamin Dunn; Philipp Berens; David Klindt; Thomas Euler; | code |
| 284 | Learning Knowledge Graph-based World Models of Textual Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work focuses on the task of building world models of text-based game environments. |
Prithviraj Ammanabrolu; Mark Riedl; | |
| 285 | Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide deeper insights into a class of acceleration schemes built on Anderson mixing that improve the convergence of deep RL algorithms. |
Ke Sun; Yafei Wang; Yi Liu; yingnan zhao; Bo Pan; Shangling Jui; Bei Jiang; Linglong Kong; | |
| 286 | Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop faster techniques for instances where components in the sum are cardinality-based, meaning they depend only on the size of the input set. |
Nate Veldt; Austin R. Benson; Jon Kleinberg; | |
| 287 | Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. |
Lulu Zheng; Jiarui Chen; Jianhao Wang; Jiamin He; Yujing Hu; Yingfeng Chen; Changjie Fan; Yang Gao; Chongjie Zhang; | |
| 288 | Two Sides of Meta-Learning Evaluation: In Vs. Out of Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our work aims to inform the meta-learning community about the importance and distinction of ID vs. OOD evaluation, as well as the subtleties of OOD evaluation with current benchmarks. |
Amrith Setlur; Oscar Li; Virginia Smith; | |
| 289 | Debiased Visual Question Answering from Feature and Sample Perspectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method named D-VQA to alleviate the above challenges from the feature and sample perspectives. |
Zhiquan Wen; Guanghui Xu; Mingkui Tan; Qingyao Wu; Qi Wu; | |
| 290 | Towards A Unified Game-Theoretic View of Adversarial Perturbations and Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. |
Jie Ren; Die Zhang; Yisen Wang; Lu Chen; Zhanpeng Zhou; Yiting Chen; Xu Cheng; Xin Wang; Meng Zhou; Jie Shi; Quanshi Zhang; | code |
| 291 | On The Out-of-distribution Generalization of Probabilistic Image Modelling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This motivates our proposal of a Local Autoregressive model that exclusively models local image features towards improving OOD performance. |
Mingtian Zhang; Andi Zhang; Steven McDonagh; | |
| 292 | Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the application of quasi-Newton methods for solving empirical risk minimization (ERM) problems defined over a large dataset. |
Qiujiang Jin; Aryan Mokhtari; | |
| 293 | PDE-GCN: Novel Architectures for Graph Neural Networks Motivated By Partial Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a family of architecturesto control this behavior by design. |
Moshe Eliasof; Eldad Haber; Eran Treister; | |
| 294 | Information Directed Reward Learning for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider an RL setting where the agent can obtain information about the reward only by querying an expert that can, for example, evaluate individual states or provide binary preferences over trajectories. |
David Lindner; Matteo Turchetta; Sebastian Tschiatschek; Kamil Ciosek; Andreas Krause; | |
| 295 | SSMF: Shifting Seasonal Matrix Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Shifting Seasonal Matrix Factorization approach, namely SSMF, that can adaptively learn multiple seasonal patterns (called regimes), as well as switching between them. |
Koki Kawabata; Siddharth Bhatia; Rui Liu; Mohit Wadhwa; Bryan Hooi; | |
| 296 | Associative Memories Via Predictive Coding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel neural model for realizing associative memories, which is based on a hierarchical generative network that receives external stimuli via sensory neurons. |
Tommaso Salvatori; Yuhang Song; Yujian Hong; Lei Sha; Simon Frieder; Zhenghua Xu; Rafal Bogacz; Thomas Lukasiewicz; | |
| 297 | Robust and Differentially Private Mean Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce PRIME, which is the first efficient algorithm that achieves both privacy and robustness for a wide range of distributions. |
Xiyang Liu; Weihao Kong; Sham Kakade; Sewoong Oh; | |
| 298 | Adaptable Agent Populations Via A Generative Model of Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to learn a space of diverse and high-reward policies in a given environment. |
Kenneth Derek; Phillip Isola; | code |
| 299 | A No-go Theorem for Robust Acceleration in The Hyperbolic Plane Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we prove that in a noisy setting, there is no analogue of accelerated gradient descent for geodesically convex functions on the hyperbolic plane. |
Linus Hamilton; Ankur Moitra; | |
| 300 | Privately Learning Mixtures of Axis-Aligned Gaussians Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of learning multivariate Gaussians under the constraint of approximate differential privacy. |
Ishaq Aden-Ali; Hassan Ashtiani; Christopher Liaw; | |
| 301 | Deep Self-Dissimilarities As Powerful Visual Fingerprints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Features extracted from deep layers of classification networks are widely used as image descriptors. Here, we exploit an unexplored property of these features: their internal dissimilarity. |
Idan Kligvasser; Tamar Shaham; Yuval Bahat; Tomer Michaeli; | |
| 302 | Invariant Causal Imitation Learning for Generalizable Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging data from multiple environments, we propose Invariant Causal Imitation Learning (ICIL), a novel technique in which we learn a feature representation that is invariant across domains, on the basis of which we learn an imitation policy that matches expert behavior. |
Ioana Bica; Daniel Jarrett; Mihaela van der Schaar; | |
| 303 | CoAtNet: Marrying Convolution and Attention for All Data Sizes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that while Transformers tend to have larger model capacity, their generalization can be worse than convolutional networks due to the lack of the right inductive bias. |
Zihang Dai; Hanxiao Liu; Quoc Le; Mingxing Tan; | |
| 304 | Mixed Supervised Object Detection By Transferring Mask Prior and Semantic Similarity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we further transfer mask prior and semantic similarity to bridge the gap between novel categories and base categories. |
Yan Liu; Zhijie Zhang; Li Niu; Junjie Chen; Liqing Zhang; | code |
| 305 | Celebrating Diversity in Shared Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to introduce diversity in both optimization and representation of shared multi-agent reinforcement learning. |
Li Chenghao; Tonghan Wang; Chengjie Wu; Qianchuan Zhao; Jun Yang; Chongjie Zhang; | |
| 306 | Rebounding Bandits for Modeling Satiation Effects Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce rebounding bandits, a multi-armed bandit setup, where satiation dynamics are modeled as time-invariant linear dynamical systems. |
Liu Leqi; Fatma Kilinc Karzan; Zachary Lipton; Alan Montgomery; | |
| 307 | Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we provide sample complexity bounds for cut-selection in branch-and-cut (B&C). |
Maria-Florina F. Balcan; Siddharth Prasad; Tuomas Sandholm; Ellen Vitercik; | |
| 308 | IQ-Learn: Inverse Soft-Q Learning for Imitation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a method for dynamics-aware IL which avoids adversarial training by learning a single Q-function, implicitly representing both reward and policy. |
Divyansh Garg; Shuvam Chakraborty; Chris Cundy; Jiaming Song; Stefano Ermon; | |
| 309 | Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Taufe, a novel regularizer that deactivates many undesirable features using OOD examples in the feature extraction layer and thus removes the dependency on the task-specific softmax layer. |
Dongmin Park; Hwanjun Song; Minseok Kim; Jae-Gil Lee; | |
| 310 | Private Non-smooth ERM and SCO in Subquadratic Steps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. |
Janardhan Kulkarni; Yin Tat Lee; Daogao Liu; | |
| 311 | Towards Instance-Optimal Offline Reinforcement Learning with Pessimism Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze the \emph{Adaptive Pessimistic Value Iteration} (APVI) algorithm and derive the suboptimality upper bound that nearly matches\[O\left(\sum_{h=1}^H\sum_{s_h, a_h}d^{\pi^\star}_h(s_h, a_h)\sqrt{\frac{\mathrm{Var}_{P_{s_h, a_h}}{(V^\star_{h+1}+r_h)}}{d^\mu_h(s_h, a_h)}}\sqrt{\frac{1}{n}}\right). |
Ming Yin; Yu-Xiang Wang; | |
| 312 | Speedy Performance Estimation for Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We instead propose to estimate the final test performance based on a simple measure of training speed. |
Robin Ru; Clare Lyle; Lisa Schut; Miroslav Fil; Mark van der Wilk; Yarin Gal; | |
| 313 | How Tight Can PAC-Bayes Be in The Small Data Regime? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the question: _Given a small number of datapoints, for example $N = 30$, how tight can PAC-Bayes and test set bounds be made? |
Andrew Foong; Wessel Bruinsma; David Burt; Richard Turner; | |
| 314 | Deep Synoptic Monte-Carlo Planning in Reconnaissance Blind Chess Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces deep synoptic Monte Carlo planning (DSMCP) for large imperfect information games. |
Gregory Clark; | |
| 315 | Dynamic Analysis of Higher-Order Coordination in Neuronal Assemblies Via De-Sparsified Orthogonal Matching Pursuit Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these shortcomings, we propose an adaptive greedy filtering algorithm based on a discretized mark point-process model of ensemble spiking and a corresponding precise statistical inference framework to identify significant coordinated higher-order spiking activity. |
Shoutik Mukherjee; Behtash Babadi; | |
| 316 | Efficient Training of Retrieval Models Using Negative Cache Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a novel negative sampling technique for accelerating training with softmax cross-entropy loss. |
Erik Lindgren; Sashank Reddi; Ruiqi Guo; Sanjiv Kumar; | |
| 317 | Understanding Partial Multi-Label Learning Via Mutual Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of adopting hand-made heuristic strategy, we propose a novel Mutual Information Label Identification for Partial Multilabel Learning (MILI-PML), which is derived from a clear probabilistic formulation and could be easily interpreted theoretically from the mutual information perspective, as well as naturally incorporates the feature/label relevancy considerations. |
Xiuwen Gong; Dong Yuan; Wei Bao; | |
| 318 | Environment Generation for Zero-Shot Compositional Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we present Compositional Design of Environments (CoDE), which trains a Generator agent to automatically build a series of compositional tasks tailored to the RL agent’s current skill level. |
Izzeddin Gur; Natasha Jaques; Yingjie Miao; Jongwook Choi; Manoj Tiwari; Honglak Lee; Aleksandra Faust; | |
| 319 | Optimizing Conditional Value-At-Risk of Black-Box Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents two Bayesian optimization (BO) algorithms with theoretical performance guarantee to maximize the conditional value-at-risk (CVaR) of a black-box function: CV-UCB and CV-TS which are based on the well-established principle of optimism in the face of uncertainty and Thompson sampling, respectively. |
Quoc Phong Nguyen; Zhongxiang Dai; Bryan Kian Hsiang Low; Patrick Jaillet; | |
| 320 | E(n) Equivariant Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs). |
Victor Garcia Satorras; Emiel Hoogeboom; Fabian Fuchs; Ingmar Posner; Max Welling; | |
| 321 | Revitalizing CNN Attention Via Transformers in Self-Supervised Visual Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL. |
Chongjian GE; Youwei Liang; YIBING SONG; Jianbo Jiao; Jue Wang; Ping Luo; | |
| 322 | A Critical Look at The Consistency of Causal Estimation with Deep Latent Variable Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate this gap between theory and empirical results with analytical considerations and extensive experiments under multiple synthetic and real-world data sets, using the causal effect variational autoencoder (CEVAE) as a case study. |
Severi Rissanen; Pekka Marttinen; | |
| 323 | Improving Robustness Using Generated Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how generative models trained solely on the original training set can be leveraged to artificially increase the size of the original training set and improve adversarial robustness to $\ell_p$ norm-bounded perturbations. |
Sven Gowal; Sylvestre-Alvise Rebuffi; Olivia Wiles; Florian Stimberg; Dan Andrei Calian; Timothy A. Mann; | |
| 324 | An Analysis of Constant Step Size SGD in The Non-convex Regime: Asymptotic Normality and Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to address this shortcoming, in this work, we establish an asymptotic normality result for the constant step size stochastic gradient descent (SGD) algorithm—a widely used algorithm in practice. |
Lu Yu; Krishnakumar Balasubramanian; Stanislav Volgushev; Murat A. Erdogdu; | |
| 325 | Learning to Learn Graph Topologies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to learn a mapping from node data to the graph structure based on the idea of learning to optimise (L2O). |
Xingyue Pu; Tianyue Cao; Xiaoyun Zhang; Xiaowen Dong; Siheng Chen; | |
| 326 | Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a generalized GAN framework for tabular synthesis, which combines the adversarial training of GANs and the negative log-density regularization of invertible neural networks. |
JAEHOON LEE; Jihyeon Hyeong; Jinsung Jeon; Noseong Park; Jihoon Cho; | |
| 327 | Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose new learning-based methods for reducing collision checking to accelerate motion planning by training graph neural networks (GNNs) that perform path exploration and path smoothing. |
Chenning Yu; Sicun Gao; | |
| 328 | Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike previous works that study ranking from multi-wise comparisons, in this paper, we do not require any parametric model or assumption and work on the fundamental setting where each comparison returns the correct result with probability $1$ or a certain probability larger than $\frac{1}{2}$. |
Wenbo Ren; Jia Liu; Ness Shroff; | |
| 329 | Efficient Bayesian Network Structure Learning Via Local Markov Boundary Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze the complexity of learning directed acyclic graphical models from observational data in general settings without specific distributional assumptions. |
Ming Gao; Bryon Aragam; | |
| 330 | Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention. |
Byung-Hoon Kim; Jong Chul Ye; Jae-Jin Kim; | code |
| 331 | Understanding The Generalization Benefit of Model Invariance from A Data Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the generalization benefit of model invariance by introducing the sample cover induced by transformations, i.e., a representative subset of a dataset that can approximately recover the whole dataset using transformations. |
Sicheng Zhu; Bang An; Furong Huang; | |
| 332 | Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents new \emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). |
Zihan Zhang; Jiaqi Yang; Xiangyang Ji; Simon S. Du; | |
| 333 | How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this light, we propose Robust Informative Fine-Tuning (RIFT), a novel adversarial fine-tuning method from an information-theoretical perspective. |
Xinshuai Dong; Anh Tuan Luu; Min Lin; Shuicheng Yan; Hanwang Zhang; | |
| 334 | Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Recursive Bayesian Networks (RBNs), which generalise and unify PCFGs and DBNs, combining their strengths and containing both as special cases. |
Robert Lieck; Martin Rohrmeier; | |
| 335 | EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we fix all these deficiencies by proposing and analyzing a new EF mechanism, which we call EF21, which consistently and substantially outperforms EF in practice. |
Peter Richtarik; Igor Sokolov; Ilyas Fatkhullin; | |
| 336 | Mixture Weights Optimisation for Alpha-Divergence Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses on $\alpha$-divergence minimisation methods for Variational Inference. More precisely, we are interested in algorithms optimising the mixture weights of any given mixture model, without any information on the underlying distribution of its mixture components parameters. |
Kam�lia Daudel; randal douc; | |
| 337 | Instance-dependent Label-noise Learning Under A Structural Causal Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to model and make use of the causal process in order to correct the label-noise effect.Empirically, the proposed method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets. |
Yu Yao; Tongliang Liu; Mingming Gong; Bo Han; Gang Niu; Kun Zhang; | |
| 338 | Combining Human Predictions with Model Probabilities Via Confusion Matrices and Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a set of algorithms that combine the probabilistic output of a model with the class-level output of a human. |
Gavin Kerrigan; Padhraic Smyth; Mark Steyvers; | |
| 339 | $\texttt{LeadCache}$: Regret-Optimal Caching in Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose $\texttt{LeadCache}$ – an efficient online caching policy based on the Follow-the-Perturbed-Leader paradigm. |
Debjit Paria; Abhishek Sinha; | |
| 340 | Probabilistic Attention for Interactive Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference. |
Prasad Gabbur; Manjot Bilkhu; Javier Movellan; | code |
| 341 | Influence Patterns for Explaining Information Flow in BERT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce influence patterns, abstractions of sets of paths through a transformer model. |
Kaiji Lu; Zifan Wang; Piotr Mardziel; Anupam Datta; | |
| 342 | Robust Regression Revisited: Acceleration and Improved Estimation Rates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present nearly-linear time algorithms for robust regression problems with improved runtime or estimation guarantees compared to the state-of-the-art. |
Arun Jambulapati; Jerry Li; Tselil Schramm; Kevin Tian; | |
| 343 | Automatic Unsupervised Outlier Model Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we tackle the unsupervised outlier model selection (UOMS) problem, and propose MetaOD, a principled, data-driven approach to UOMS based on meta-learning. |
Yue Zhao; Ryan Rossi; Leman Akoglu; | |
| 344 | Pruning Randomly Initialized Neural Networks with Iterative Randomization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this parameter inefficiency, we introduce a novel framework to prune randomly initialized neural networks with iteratively randomizing weight values (IteRand). |
Daiki Chijiwa; Shin'ya Yamaguchi; Yasutoshi Ida; Kenji Umakoshi; Tomohiro INOUE; | |
| 345 | Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this, we propose a fully Transformer visual embedding for VLP to better learn visual relation and further promote inter-modal alignment. |
Hongwei Xue; Yupan Huang; Bei Liu; Houwen Peng; Jianlong Fu; Houqiang Li; Jiebo Luo; | |
| 346 | Stability and Generalization of Bilevel Programming in Hyperparameter Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper attempts to address the issue by presenting an expectation bound w.r.t. the validation set based on uniform stability. |
Fan Bao; Guoqiang Wu; Chongxuan LI; Jun Zhu; Bo Zhang; | |
| 347 | Regime Switching Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a learning algorithm for this problem, building on spectral method-of-moments estimations for hidden Markov models, belief error control in partially observable Markov decision processes and upper-confidence-bound methods for online learning. |
Xiang Zhou; Yi Xiong; Ningyuan Chen; Xuefeng GAO; | |
| 348 | MixACM: Mixup-Based Robustness Transfer Via Distillation of Activated Channel Maps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore this question from the perspective of knowledge transfer. |
Awais Muhammad; Fengwei Zhou; Chuanlong Xie; Jiawei Li; Sung-Ho Bae; Zhenguo Li; | |
| 349 | Localization, Convexity, and Star Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that the offset complexity can be generalized to any loss that satisfies a certain general convexity condition. |
Suhas Vijaykumar; | |
| 350 | Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we propose a novel target adaptation framework that relies only on silhouette supervision to adapt a source-trained model-based regressor. |
Mugalodi Rakesh; Jogendra Nath Kundu; Varun Jampani; Venkatesh Babu R; | |
| 351 | Self-Adaptable Point Processes with Nonparametric Time Decays Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we propose SPRITE, a $\underline{S}$elf-adaptable $\underline{P}$oint p$\underline{R}$ocess w$\underline{I}$th nonparametric $\underline{T}$ime d$\underline{E}$cays, which can decouple the influences between every pair of the events and capture various time decays of the influence strengths. |
Zhimeng Pan; Zheng Wang; Jeff M. Phillips; Shandian Zhe; | |
| 352 | Offline Meta Reinforcement Learning — Identifiability Challenges and Effective Data Collection Strategies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on the recent VariBAD BRL approach, we develop an off-policy BRL method that learns to plan an exploration strategy based on an adaptive neural belief estimate. |
Ron Dorfman; Idan Shenfeld; Aviv Tamar; | code |
| 353 | RoMA: Robust Model Adaptation for Offline Model-based Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle the issue, we propose a new framework, coined robust model adaptation (RoMA), based on gradient-based optimization of inputs over the DNN. |
Sihyun Yu; Sungsoo Ahn; Le Song; Jinwoo Shin; | |
| 354 | Flexible Option Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit and extend intra-option learning in the context of deep reinforcement learning, in order to enable updating all options consistent with current primitive action choices, without introducing any additional estimates. |
Martin Klissarov; Doina Precup; | |
| 355 | Faster Directional Convergence of Linear Neural Networks Under Spherically Symmetric Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study gradient methods for training deep linear neural networks with binary cross-entropy loss. |
Dachao Lin; Ruoyu Sun; Zhihua Zhang; | |
| 356 | Online Facility Location with Multiple Advice Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the classic facility location problem in the presence of multiple machine-learned advice. |
Matteo Almanza; Flavio Chierichetti; Silvio Lattanzi; Alessandro Panconesi; Giuseppe Re; | |
| 357 | Credit Assignment in Neural Networks Through Deep Feedback Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce Deep Feedback Control (DFC), a new learning method that uses a feedback controller to drive a deep neural network to match a desired output target and whose control signal can be used for credit assignment. |
Alexander Meulemans; Matilde Tristany Farinha; Javier Garcia Ordonez; Pau Vilimelis Aceituno; Jo�o Sacramento; Benjamin F. Grewe; | |
| 358 | Robust Online Correlation Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we go beyond worst case analysis, and show that the celebrated Pivot algorithm performs well when given access to a small number of random samples from the input. |
Silvio Lattanzi; Benjamin Moseley; Sergei Vassilvitskii; Yuyan Wang; Rudy Zhou; | |
| 359 | Neural Additive Models: Interpretable Machine Learning with Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Neural Additive Models (NAMs) which combine some of the expressivity of DNNs with the inherent intelligibility of generalized additive models. |
Rishabh Agarwal; Levi Melnick; Nicholas Frosst; Xuezhou Zhang; Ben Lengerich; Rich Caruana; Geoffrey E. Hinton; | |
| 360 | Representation Learning for Event-based Visuomotor Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an event variational autoencoder through which compact representations can be learnt directly from asynchronous spatiotemporal event data. |
Sai Vemprala; Sami Mian; Ashish Kapoor; | |
| 361 | Kernel Functional Optimisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel formulation for kernel selection using efficient Bayesian optimisation to find the best fitting non-parametric kernel. |
Arun Kumar Anjanapura Venkatesh; Alistair Shilton; Santu Rana; Sunil Gupta; Svetha Venkatesh; | |
| 362 | Generalized Shape Metrics on Neural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A standardized set of analysis tools is now needed to identify how network-level covariates—such as architecture, anatomical brain region, and model organism—impact neural representations (hidden layer activations). Here, we provide a rigorous foundation for these analyses by defining a broad family of metric spaces that quantify representational dissimilarity. |
Alex Williams; Erin Kunz; Simon Kornblith; Scott Linderman; | |
| 363 | Diverse Message Passing for Attribute with Heterophily Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, the network homophily rate defined with respect to the node labels is extended to attribute homophily rate by taking the attributes as weak labels. |
Liang Yang; Mengzhe Li; Liyang Liu; bingxin niu; Chuan Wang; Xiaochun Cao; Yuanfang Guo; | |
| 364 | Towards Robust Bisimulation Metric Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we generalize value function approximation bounds for on-policy bisimulation metrics to non-optimal policies and approximate environment dynamics. |
Mete Kemertas; Tristan Aumentado-Armstrong; | |
| 365 | Beyond BatchNorm: Towards A Unified Understanding of Normalization in Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a first step towards this goal by extending known properties of BatchNorm in randomly initialized deep neural networks (DNNs) to several recently proposed normalization layers. |
Ekdeep Lubana; Robert Dick; Hidenori Tanaka; | |
| 366 | Representation Learning Beyond Linear Prediction Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that diversity holds even if the target task uses a neural network with multiple layers, as long as source tasks use linear functions. |
Ziping Xu; Ambuj Tewari; | |
| 367 | Volume Rendering of Neural Implicit Surfaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The goal of this paper is to improve geometry representation and reconstruction in neural volume rendering. |
Lior Yariv; Jiatao Gu; Yoni Kasten; Yaron Lipman; | |
| 368 | MAUVE: Measuring The Gap Between Neural Text and Human Text Using Divergence Frontiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Mauve, a comparison measure for open-ended text generation, which directly compares the learnt distribution from a text generation model to the distribution of human-written text using divergence frontiers. |
Krishna Pillutla; Swabha Swayamdipta; Rowan Zellers; John Thickstun; Sean Welleck; Yejin Choi; Zaid Harchaoui; | |
| 369 | Accurately Solving Rod Dynamics with Graph Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this contribution, we introduce a novel method to accelerate iterative solvers for rod dynamics with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations. |
Han Shao; Tassilo Kugelstadt; Torsten H�drich; Wojtek Palubicki; Jan Bender; Soeren Pirk; Dominik Michels; | |
| 370 | Limiting Fluctuation and Trajectorial Stability of Multilayer Neural Networks with Mean Field Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we initiate the study of the fluctuation in the case of multilayer networks, at any network depth. |
Huy Pham; Phan-Minh Nguyen; | |
| 371 | Medical Dead-ends and Learning to Identify High-Risk States and Treatments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an inherently different approach that identifies "dead-ends" of a state space. |
Mehdi Fatemi; Taylor W. Killian; Jayakumar Subramanian; Marzyeh Ghassemi; | |
| 372 | Overcoming The Convex Barrier for Simplex Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Buoyed by this success, we consider the problem of developing similar techniques for verifying robustness to input perturbations within the probability simplex. |
Harkirat Singh Behl; M. Pawan Kumar; Philip Torr; Krishnamurthy Dvijotham; | |
| 373 | High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider non-convex stochastic optimization using first-order algorithms for which the gradient estimates may have heavy tails. |
Ashok Cutkosky; Harsh Mehta; | |
| 374 | Batch Normalization Orthogonalizes Representations in Deep Random Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper underlines an elegant property of batch-normalization (BN): Successive batch normalizations with random linear updates make samples increasingly orthogonal. |
Hadi Daneshmand; Amir Joudaki; Francis Bach; | |
| 375 | Support Vector Machines and Linear Regression Coincide with Very High-dimensional Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the generality of this phenomenon and make the following contributions. |
Navid Ardeshir; Clayton Sanford; Daniel J. Hsu; | |
| 376 | Coupled Segmentation and Edge Learning Via Dynamic Graph Propagation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a principled end-to-end framework for coupled edge and segmentation learning, where edges are leveraged as pairwise similarity cues to guide segmentation. |
Zhiding Yu; Rui Huang; Wonmin Byeon; Sifei Liu; Guilin Liu; Thomas Breuel; Anima Anandkumar; Jan Kautz; | |
| 377 | Offline RL Without Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we show that simply doing one step of constrained/regularized policy improvement using an on-policy Q estimate of the behavior policy performs surprisingly well. |
David Brandfonbrener; William F. Whitney; Rajesh Ranganath; Joan Bruna; | |
| 378 | Continuous Vs. Discrete Optimization of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The extent to which it represents gradient descent is an open question in the theory of deep learning. The current paper studies this question. |
Omer Elkabetz; Nadav Cohen; | |
| 379 | CrypTen: Secure Multi-Party Computation Meets Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To foster adoption of secure MPC in machine learning, we present CrypTen: a software framework that exposes popular secure MPC primitives via abstractions that are common in modern machine-learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks. |
Brian Knott; Shobha Venkataraman; Awni Hannun; Shubho Sengupta; Mark Ibrahim; Laurens van der Maaten; | |
| 380 | Can Contrastive Learning Avoid Shortcut Solutions? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we propose implicit feature modification (IFM), a method for altering positive and negative samples in order to guide contrastive models towards capturing a wider variety of predictive features. |
Joshua Robinson; Li Sun; Ke Yu; Kayhan Batmanghelich; Stefanie Jegelka; Suvrit Sra; | |
| 381 | See More for Scene: Pairwise Consistency Learning for Scene Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to understand scene images and the scene classification CNN models in terms of the focus area. |
Gongwei Chen; Xinhang Song; Bohan Wang; Shuqiang Jiang; | |
| 382 | Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a loss that performs spectral decomposition on the population augmentation graph and can be succinctly written as a contrastive learning objective on neural net representations. |
Jeff Z. HaoChen; Colin Wei; Adrien Gaidon; Tengyu Ma; | |
| 383 | Greedy Approximation Algorithms for Active Sequential Hypothesis Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by applications in which the number of hypotheses or actions is massive (e.g., genomics-based cancer detection), we propose efficient (greedy, in fact) algorithms and provide the first approximation guarantees for ASHT, under two types of adaptivity. |
Kyra Gan; Su Jia; Andrew Li; | |
| 384 | When False Positive Is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose a novel framework on top of the deep learning framework named \textit{Cross-Batch Approximation for Multipartite Ranking (CBA-MR)}. |
Peisong Wen; Qianqian Xu; Zhiyong Yang; Yuan He; Qingming Huang; | |
| 385 | Convex Polytope Trees and Its Application to VAE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose convex polytope trees (CPT) to expand the family of decision trees by an interpretable generalization of their decision boundary. |
Mohammadreza Armandpour; Ali Sadeghian; Mingyuan Zhou; | |
| 386 | The Skellam Mechanism for Differentially Private Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the multi-dimensional Skellam mechanism, a discrete differential privacy mechanism based on the difference of two independent Poisson random variables. |
Naman Agarwal; Peter Kairouz; Ziyu Liu; | |
| 387 | Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$ Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that if the so-called Bernstein condition is satisfied, the term $\Theta(1/\sqrt{n})$ can be avoided, and high probability excess risk bounds of order up to $O(1/n)$ are possible via uniform stability. |
Yegor Klochkov; Nikita Zhivotovskiy; | |
| 388 | SketchGen: Generating Constrained CAD Sketches Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose SketchGen as a generative model based on a transformer architecture to address the heterogeneity problem by carefully designing a sequential language for the primitives and constraints that allows distinguishing between different primitive or constraint types and their parameters, while encouraging our model to re-use information across related parameters, encoding shared structure. |
Wamiq Para; Shariq Bhat; Paul Guerrero; Tom Kelly; Niloy Mitra; Leonidas J. Guibas; Peter Wonka; | |
| 389 | CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a simple Contrastive Learning framework for semi-supervised Domain Adaptation (CLDA) that attempts to bridge the intra-domain gap between the labeled and unlabeled target distributions and the inter-domain gap between source and unlabeled target distribution in SSDA. |
Ankit Singh; | |
| 390 | Differentially Private N-gram Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a new differentially private algorithm for this problem which, in our experiments, significantly outperforms the state-of-the-art. |
Kunho Kim; Sivakanth Gopi; Janardhan Kulkarni; Sergey Yekhanin; | |
| 391 | Capturing Implicit Hierarchical Structure in 3D Biomedical Images with Self-supervised Hyperbolic Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. |
Joy Hsu; Jeffrey Gu; Gong Wu; Wah Chiu; Serena Yeung; | |
| 392 | Noisy Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. |
Soon Hoe Lim; N. Benjamin Erichson; Liam Hodgkinson; Michael W. Mahoney; | |
| 393 | Matrix Encoding Networks for Neural Combinatorial Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Matrix Encoding Network (MatNet) and show how conveniently it takes in and processes parameters of such complex CO problems. |
Yeong-Dae Kwon; Jinho Choo; Iljoo Yoon; Minah Park; Duwon Park; Youngjune Gwon; | |
| 394 | When Is Unsupervised Disentanglement Possible? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that the assumption of local isometry together with non-Gaussianity of the factors, is sufficient to provably recover disentangled representations from data. |
Daniella Horan; Eitan Richardson; Yair Weiss; | |
| 395 | Continuous Latent Process Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To optimize our model using maximum likelihood, we propose a novel piecewise construction of a variational posterior process and derive the corresponding variational lower bound using trajectory re-weighting. |
Ruizhi Deng; Marcus A. Brubaker; Greg Mori; Andreas Lehrmann; | |
| 396 | Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study predictive control in a setting where the dynamics are time-varying and linear, and the costs are time-varying and well-conditioned. |
Yiheng Lin; Yang Hu; Guanya Shi; Haoyuan Sun; Guannan Qu; Adam Wierman; | |
| 397 | Dataset Distillation with Infinitely Wide Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To that end, we apply a novel distributed kernel-based meta-learning framework to achieve state-of-the-art results for dataset distillation using infinitely wide convolutional neural networks. |
Timothy Nguyen; Roman Novak; Lechao Xiao; Jaehoon Lee; | |
| 398 | SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simple but efficient memory-disk hybrid indexing and search system, named SPANN, that follows the inverted index methodology. |
Qi Chen; Bing Zhao; Haidong Wang; Mingqin Li; Chuanjie Liu; Zhiyong Zheng; Mao Yang; Jingdong Wang; | code |
| 399 | Distilling Object Detectors with Feature Richness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above issues, we propose a novel Feature-Richness Score (FRS) method to choose important features that improve generalized detectability during distilling. |
Du Zhixing; Rui Zhang; Ming Chang; xishan zhang; Shaoli Liu; Tianshi Chen; Yunji Chen; | |
| 400 | Analysis of One-hidden-layer Neural Networks Via The Resolvent Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the asymptotic spectral density of the random feature matrix $M = Y Y^*$ with $Y = f(WX)$ generated by a single-hidden-layer neural network, where $W$ and $X$ are random rectangular matrices with i.i.d. centred entries and $f$ is a non-linear smooth function which is applied entry-wise. |
Vanessa Piccolo; Dominik Schr�der; | |
| 401 | Grounding Spatio-Temporal Language with Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make progress in this direction, we here introduce a novel spatio-temporal language grounding task where the goal is to learn the meaning of spatio-temporal descriptions of behavioral traces of an embodied agent. |
Tristan Karch; Laetitia Teodorescu; Katja Hofmann; Cl�ment Moulin-Frier; Pierre-Yves Oudeyer; | |
| 402 | Learning Where to Learn: Gradient Sparsity in Meta and Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this form of meta-learning can be improved by letting the learning algorithm decide which weights to change, i.e., by learning where to learn. |
Johannes von Oswald; Dominic Zhao; Seijin Kobayashi; Simon Schug; Massimo Caccia; Nicolas Zucchet; Jo�o Sacramento; | |
| 403 | Domain Invariant Representation Learning with Domain Density Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a theoretically grounded method to learn a domain-invariant representation by enforcing the representation network to be invariant under all transformation functions among domains. |
A. Tuan Nguyen; Toan Tran; Yarin Gal; Atilim Gunes Baydin; | |
| 404 | PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. |
Tao Yu; Cuiling Lan; Wenjun Zeng; Mingxiao Feng; Zhizheng Zhang; Zhibo Chen; | |
| 405 | Efficient Equivariant Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a general framework of previous equivariant models, which includes G-CNNs and equivariant self-attention layers as special cases. |
Lingshen He; Yuxuan Chen; zhengyang shen; Yiming Dong; Yisen Wang; Zhouchen Lin; | |
| 406 | Unifying Gradient Estimators for Meta-Reinforcement Learning Via Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide a unifying framework for estimating higher-order derivatives of value functions, based on off-policy evaluation. |
Yunhao Tang; Tadashi Kozuno; Mark Rowland; Remi Munos; Michal Valko; | |
| 407 | Even Your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed By Self-Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider an iterative variant of self-distillation in a kernel regression setting, in which successive steps incorporate both model outputs and the ground-truth targets. |
Kenneth Borup; Lars Andersen; | |
| 408 | Compressing Neural Networks: Towards Determining The Optimal Layer-wise Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression. |
Lucas Liebenwein; Alaa Maalouf; Dan Feldman; Daniela Rus; | |
| 409 | Equilibrium and Non-Equilibrium Regimes in The Learning of Restricted Boltzmann Machines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that this mixing time plays a crucial role in the behavior and stability of the trained model, and that RBMs operate in two well-defined distinct regimes, namely equilibrium and out-of-equilibrium, depending on the interplay between this mixing time of the model and the number of MCMC steps, $k$, used to approximate the gradient. |
Aur�lien Decelle; Cyril Furtlehner; Beatriz Seoane; | |
| 410 | Imitation with Neural Density Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new framework for Imitation Learning (IL) via density estimation of the expert’s occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. |
Kuno Kim; Akshat Jindal; Yang Song; Jiaming Song; Yanan Sui; Stefano Ermon; | |
| 411 | Accurate Point Cloud Registration with Robust Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work investigates the use of robust optimal transport (OT) for shape matching. |
Zhengyang Shen; Jean Feydy; Peirong Liu; Ariel Curiale; Ruben San Jose Estepar; Raul San Jose Estepar; Marc Niethammer; | code |
| 412 | Simple Steps Are All You Need: Frank-Wolfe and Generalized Self-concordant Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We establish the convergence rate of a simple Frank-Wolfe variant that uses the open-loop step size strategy $\gamma_t = 2/(t+2)$, obtaining a $\mathcal{O}(1/t)$ convergence rate for this class of functions in terms of primal gap and Frank-Wolfe gap, where $t$ is the iteration count. |
Alejandro Carderera; Mathieu Besan�on; Sebastian Pokutta; | |
| 413 | Automatic Data Augmentation for Generalization in Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce three approaches for automatically finding an effective augmentation for any RL task. |
Roberta Raileanu; Maxwell Goldstein; Denis Yarats; Ilya Kostrikov; Rob Fergus; | |
| 414 | Blending Anti-Aliasing Into Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties. |
Shengju Qian; Hao Shao; Yi Zhu; Mu Li; Jiaya Jia; | |
| 415 | A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we advocate instead for a hybrid approach based on sparse coding principles that retain the interpretability of classical techniques encoding domain knowledge with handcrafted image priors, while allowing to train model parameters end-to-end without massive amounts of data. |
Theo Bodrito; Alexandre Zouaoui; Jocelyn Chanussot; Julien Mairal; | |
| 416 | Posterior Collapse and Latent Variable Non-identifiability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider posteriorcollapse as a problem of latent variable non-identifiability. |
Yixin Wang; David Blei; John P. Cunningham; | |
| 417 | The Benefits of Implicit Regularization from SGD in Least Squares Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we seek to understand these issues in the simpler setting of linear regression (including both underparameterized and overparameterized regimes), where our goal is to make sharp instance-based comparisons of the implicit regularization afforded by (unregularized) average SGD with the explicit regularization of ridge regression. |
Difan Zou; Jingfeng Wu; Vladimir braverman; Quanquan Gu; Dean P. Foster; Sham Kakade; | |
| 418 | Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the generalization properties of Model-Agnostic Meta-Learning (MAML) algorithms for supervised learning problems. |
Alireza Fallah; Aryan Mokhtari; Asuman Ozdaglar; | |
| 419 | Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this problem through a factor baseline which exploits independence structure encoded in a novel action-target influence network. |
Thomas Spooner; Nelson Vadori; Sumitra Ganesh; | |
| 420 | MarioNette: Self-Supervised Sprite Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a deep learning approach that decomposes sprite-based video animations into a disentangled representation of recurring graphic elements in a self-supervised manner. |
Dmitriy Smirnov; MICHAEL GHARBI; Matthew Fisher; Vitor Guizilini; Alexei Efros; Justin M. Solomon; | |
| 421 | RLlib Flow: Distributed Reinforcement Learning Is A Dataflow Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we re-examine the challenges posed by distributed RL and try to view it through the lens of an old idea: distributed dataflow. |
Eric Liang; Zhanghao Wu; Michael Luo; Sven Mika; Joseph E. Gonzalez; Ion Stoica; | code |
| 422 | Improve Agents Without Retraining: Parallel Tree Search with Off-Policy Correction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we introduce a novel off-policy correction term that accounts for the mismatch between the pre-trained value and its corresponding TS policy by penalizing under-sampled trajectories. |
Gal Dalal; Assaf Hallak; Steven Dalton; iuri frosio; Shie Mannor; Gal Chechik; | |
| 423 | Redesigning The Transformer Architecture with Insights from Multi-particle Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the problem of approximating the two central components of the Transformer — multi-head self-attention and point-wise feed-forward transformation, with reduced parameter space and computational complexity. |
Subhabrata Dutta; Tanya Gautam; Soumen Chakrabarti; Tanmoy Chakraborty; | |
| 424 | Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this gap via a comprehensive investigation on the impact of network width and depth on the robustness of adversarially trained DNNs. |
Hanxun Huang; Yisen Wang; Sarah Erfani; Quanquan Gu; James Bailey; Xingjun Ma; | |
| 425 | Center Smoothing: Certified Robustness for Networks with Structured Outputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc. |
Aounon Kumar; Tom Goldstein; | |
| 426 | Breaking The Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on improving the per iteration cost of CGM. |
Zhaozhuo Xu; Zhao Song; Anshumali Shrivastava; | |
| 427 | Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we perform a large-scale benchmarking of dozens of deep neural network models in mouse visual cortex with both representational similarity analysis and neural regression. |
Colin Conwell; David Mayo; Andrei Barbu; Michael Buice; George Alvarez; Boris Katz; | |
| 428 | A Topological Perspective on Causal Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs). |
Duligur Ibeling; Thomas Icard; | |
| 429 | Parameter Inference with Bifurcation Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a gradient-based approach for inferring the parameters of differential equations that produce a user-specified bifurcation diagram. |
Gregory Szep; Neil Dalchau; Attila Csik�sz-Nagy; | |
| 430 | Scalable Thompson Sampling Using Sparse Gaussian Process Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform a theoretical and empirical analysis of scalable TS. |
Sattar Vakili; Henry Moss; Artem Artemev; Vincent Dutordoir; Victor Picheny; | |
| 431 | Robust Counterfactual Explanations on Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel method to generate robust counterfactual explanations on GNNs by explicitly modelling the common decision logic of GNNs on similar input graphs. |
Mohit Bajaj; Lingyang Chu; Zi Yu Xue; Jian Pei; Lanjun Wang; Peter Cho-Ho Lam; Yong Zhang; | |
| 432 | Similarity and Matching of Neural Network Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We employ a toolset — dubbed Dr. Frankenstein — to analyse the similarity of representations in deep neural networks. With this toolset we aim to match the activations on given layers of two trained neural networks by joining them with a stitching layer. |
Adri�n Csisz�rik; P�ter Kor�si-Szab�; �kos Matszangosz; Gergely Papp; D�niel Varga; | |
| 433 | DOCTOR: A Simple Method for Detecting Misclassification Errors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose DOCTOR, a simple method that aims to identify whether the prediction of a DNN classifier should (or should not) be trusted so that, consequently, it would be possible to accept it or to reject it. |
Federica Granese; Marco Romanelli; Daniele Gorla; Catuscia Palamidessi; Pablo Piantanida; | |
| 434 | Contrastive Laplacian Eigenmaps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend the celebrated Laplacian Eigenmaps with contrastive learning, and call them COntrastive Laplacian EigenmapS (COLES). |
Hao Zhu; Ke Sun; Peter Koniusz; | |
| 435 | Machine Learning Structure Preserving Brackets for Forecasting Irreversible Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present a novel parameterization of dissipative brackets from metriplectic dynamical systems appropriate for learning \emph{irreversible} dynamics with unknown a priori model form. |
Kookjin Lee; Nathaniel Trask; Panos Stinis; | |
| 436 | On The Variance of The Fisher Information for Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In practice, it is almost always estimated based on empirical samples. We investigate two such estimators based on two equivalent representations of the FIM — both unbiased and consistent. |
Alexander Soen; Ke Sun; | |
| 437 | A$^2$-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Attribute-Aware hashing Network (A$^2$-Net) for generating attribute-aware hash codes to not only make the retrieval process efficient, but also establish explicit correspondences between hash codes and visual attributes. |
Xiu-Shen Wei; Yang Shen; Xuhao Sun; Han-Jia Ye; Jian Yang; | |
| 438 | Shape Registration in The Time of Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. |
Giovanni Trappolini; Luca Cosmo; Luca Moschella; Riccardo Marin; Simone Melzi; Emanuele Rodol�; | |
| 439 | Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such a problem, we introduce a novel formulation, combinatorial construction, which requires a building agent to assemble unit primitives (i.e., LEGO bricks) sequentially — every connection between two bricks must follow a fixed rule, while no bricks mutually overlap. |
Hyunsoo Chung; Jungtaek Kim; Boris Knyazev; Jinhwi Lee; Graham W. Taylor; Jaesik Park; Minsu Cho; | |
| 440 | Dissecting The Diffusion Process in Linear Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we dissect the feature propagation steps of linear GCNs from a perspective of continuous graph diffusion, and analyze why linear GCNs fail to benefit from more propagation steps. |
Yifei Wang; Yisen Wang; Jiansheng Yang; Zhouchen Lin; | |
| 441 | Dynamic Grained Encoder for Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces sparse queries for vision transformers to exploit the intrinsic spatial redundancy of natural images and save computational costs. |
Lin Song; Songyang Zhang; Songtao Liu; Zeming Li; Xuming He; Hongbin Sun; Jian Sun; Nanning Zheng; | code |
| 442 | Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a novel framework to analyze this empirical result regarding negative samples using the coupon collector’s problem. |
Kento Nozawa; Issei Sato; | |
| 443 | On UMAP's True Loss Function Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate UMAP’s sampling based optimization scheme in detail. |
Sebastian Damrich; Fred A. Hamprecht; | |
| 444 | Fast Pure Exploration Via Frank-Wolfe Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of active pure exploration with fixed confidence in generic stochastic bandit environments. |
Po-An Wang; Ruo-Chun Tzeng; Alexandre Proutiere; | |
| 445 | IFlow: Numerically Invertible Flows for Efficient Lossless Compression Via A Uniform Coder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss lossless compression using normalizing flows which have demonstrated a great capacity for achieving high compression ratios. |
Shifeng Zhang; Ning Kang; Tom Ryder; Zhenguo Li; | |
| 446 | History Aware Multimodal Transformer for Vision-and-Language Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we introduce a History Aware Multimodal Transformer (HAMT) to incorporate a long-horizon history into multimodal decision making. |
Shizhe Chen; Pierre-Louis Guhur; Cordelia Schmid; Ivan Laptev; | |
| 447 | Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two specific algorithms for this task: a generic scheme which improves over baselines, and a more tailored approach which performs even better. |
Feng Liu; Wenkai Xu; Jie Lu; Danica J. Sutherland; | |
| 448 | Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets, an iterative process to significantly change model behavior by crafting and fine-tuning on a dataset that reflects a predetermined set of target values. |
Irene Solaiman; Christy Dennison; | |
| 449 | The Lazy Online Subgradient Algorithm Is Universal on Strongly Convex Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study Online Lazy Gradient Descent for optimisation on a strongly convex domain. |
Daron Anderson; Douglas Leith; | |
| 450 | Computer-Aided Design As Language Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a machine learning model capable of automatically generating such sketches. |
Yaroslav Ganin; Sergey Bartunov; Yujia Li; Ethan Keller; Stefano Saliceti; | |
| 451 | COHESIV: Contrastive Object and Hand Embedding Segmentation In Video Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we learn to segment hands and hand-held objects from motion. |
Dandan Shan; Richard Higgins; David Fouhey; | |
| 452 | ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Bayesian Pseudocoresets Exemplar VAE (ByPE-VAE), a new variant of VAE with a prior based on Bayesian pseudocoreset. |
Qingzhong Ai; LIRONG HE; SHIYU LIU; Zenglin Xu; | code |
| 453 | Recovery Analysis for Plug-and-Play Priors Using The Restricted Eigenvalue Condition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this gap by showing how to establish theoretical recovery guarantees for PnP/RED by assuming that the solution of these methods lies near the fixed-points of a deep neural network. |
Jiaming Liu; Salman Asif; Brendt Wohlberg; Ulugbek Kamilov; | |
| 454 | Group Equivariant Subsampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we first introduce translation equivariant subsampling/upsampling layers that can be used to construct exact translation equivariant CNNs. We then generalise these layers beyond translations to general groups, thus proposing group equivariant subsampling/upsampling. |
Jin Xu; Hyunjik Kim; Thomas Rainforth; Yee Teh; | |
| 455 | Data Sharing and Compression for Cooperative Networked Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a solution to learn succinct, highly-compressed forecasts that are co-designed with a modular controller’s task objective. |
Jiangnan Cheng; Marco Pavone; Sachin Katti; Sandeep Chinchali; Ao Tang; | |
| 456 | Hyperbolic Procrustes Analysis Using Riemannian Geometry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we take a purely geometric approach for label-free alignment of hierarchical datasets and introduce hyperbolic Procrustes analysis (HPA). |
Ya-Wei Eileen Lin; Yuval Kluger; Ronen Talmon; | |
| 457 | No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model. |
Mi Luo; Fei Chen; Dapeng Hu; Yifan Zhang; Jian Liang; Jiashi Feng; | |
| 458 | Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an inexpensive preconditioner for the matrix sensing variant of nonconvex matrix factorization that restores the convergence rate of gradient descent back to linear, even in the over-parameterized case, while also making it agnostic to possible ill-conditioning in the ground truth. |
Jialun Zhang; Salar Fattahi; Richard Zhang; | |
| 459 | Improving Contrastive Learning on Imbalanced Data Via Open-World Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present an open-world unlabeled data sampling framework called Model-Aware K-center (MAK), which follows three simple principles: (1) tailness, which encourages sampling of examples from tail classes, by sorting the empirical contrastive loss expectation (ECLE) of samples over random data augmentations; (2) proximity, which rejects the out-of-distribution outliers that may distract training; and (3) diversity, which ensures diversity in the set of sampled examples. |
Ziyu Jiang; Tianlong Chen; Ting Chen; Zhangyang Wang; | code |
| 460 | Searching for Efficient Transformers for Language Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we aim to reduce the costs of Transformers by searching for a more efficient variant. |