Most Influential UAI Papers (2026-03 Version)
The Annual Conference on Uncertainty in Artificial Intelligence (UAI) is one of the top machine learning conferences in the world. Paper Digest Team analyzes all papers published on UAI in the past years, and presents the 15 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-03)
To search or review papers within UAI related to a specific topic, please use the search by venue (UAI) and review by venue (UAI) services. To browse the most productive UAI authors by year ranked by #papers accepted, here are the most productive UAI authors grouped by year.
As a pioneer in the field since 2018, Paper Digest has curated thousands of such lists, drawing on years of accumulated data across decades of conferences and research topics.To ensure users never miss a breakthrough, our daily digest service sifts through tens of thousands of new papers, clinical trials, news articles, community posts every day – delivering only what matters most to your specific interests. Beyond discovery, Paper Digest offers built-in research tools to help users read articles, write articles, get answers, conduct literature reviews, and generate research reports more efficiently.
Paper Digest Team
New York City, New York, 10017
TABLE 1: Most Influential UAI Papers (2026-03 Version)
| Year | Rank | Paper | Author(s) |
|---|---|---|---|
| 2025 | 1 | A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Large language models (LLMs) have played a pivotal role in revolutionizing various facets of our daily existence. Solving attention regression is a fundamental task in optimizing … |
Yeqi Gao; Zhao Song; Weixin Wang; Junze Yin; |
| 2025 | 2 | Creative Agents: Empowering Agents with Imagination for Creative Tasks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce several approaches to implementing the components of creative agents. |
Penglin Cai; Chi Zhang; Yuhui Fu; Haoqi Yuan; Zongqing Lu; |
| 2025 | 3 | On Information-Theoretic Measures of Predictive Uncertainty IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we revisit core concepts to propose a framework for information-theoretic measures of predictive uncertainty. |
Kajetan Schweighofer; Lukas Aichberger; Mykyta Ielanskyi; Sepp Hochreiter; |
| 2025 | 4 | Multi-group Uncertainty Quantification for Long-form Text Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our work, given some long-form text generated by an LLM, we study uncertainty at both the level of individual claims contained within the output (via calibration) and across the entire output itself (via conformal prediction). |
Terrance Liu; Steven Wu; |
| 2025 | 5 | Can A Bayesian Oracle Prevent Harm from An Agent? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. |
YOSHUA BENGIO et. al. |
| 2024 | 1 | Discrete Probabilistic Inference As Control in Multi-path Environments IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we extend recent methods correcting the reward in order to guarantee that the marginal distribution induced by the optimal MaxEnt RL policy is proportional to the original reward, regardless of the structure of the underlying MDP. |
Tristan Deleu; Padideh Nouri; Nikolay Malkin; Doina Precup; Yoshua Bengio; |
| 2024 | 2 | BEARS Make Neuro-Symbolic Models Aware of Their Reasoning Shortcuts IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Neuro-Symbolic (NeSy) predictors that conform to symbolic knowledge {–} encoding, e.g., safety constraints {–} can be affected by Reasoning Shortcuts (RSs): They learn concepts consistent with the symbolic knowledge by exploiting unintended semantics. RSs compromise reliability and generalization and, as we show in this paper, they are linked to NeSy models being overconfident about the predicted concepts. |
EMANUELE MARCONATO et. al. |
| 2024 | 3 | Amortized Variational Inference: When and Why? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we study when and why A-VI can be used for approximate Bayesian inference. |
Charles C. Margossian; David M. Blei; |
| 2024 | 4 | Neural Optimal Transport with Lagrangian Costs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our contributions are of computational interest, where we demonstrate the ability to efficiently compute geodesics and amortize spline-based paths, which has not been done before, even in low dimensional problems. |
Aram-Alexandre Pooladian; Carles Domingo-Enrich; Ricky T. Q. Chen; Brandon Amos; |
| 2024 | 5 | Towards Minimax Optimality of Model-based Robust Reinforcement Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we consider uncertainty sets defined with an $L_p$-ball (recovering the TV case), and study the sample complexity of any planning algorithm (with high accuracy guarantee on the solution) applied to an empirical RMDP estimated using the generative model. |
Pierre Clavier; Erwan Le Pennec; Matthieu Geist; |
| 2024 | 6 | Pix2Code: Learning to Compose Neural Visual Concepts As Programs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To tackle both the generalizability and interpretability constraints of visual concept learning, we propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of both explicit, compositional symbolic and implicit neural representations. |
Antonia W�st; Wolfgang Stammer; Quentin Delfosse; Devendra Singh Dhami; Kristian Kersting; |
| 2024 | 7 | Adjustment Identification Distance: A Gadjid for Causal Structure Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a framework for developing causal distances between graphs which includes the structural intervention distance for directed acyclic graphs as a special case. |
Leonard Henckel; Theo W�rtzen; Sebastian Weichwald; |
| 2024 | 8 | On Convergence of Federated Averaging Langevin Dynamics IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a federated averaging Langevin algorithm (FA-LD) for uncertainty quantification and mean predictions with distributed clients. |
Wei Deng; Qian Zhang; Yian Ma; Zhao Song; Guang Lin; |
| 2024 | 9 | Approximate Bayesian Computation with Path Signatures IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose to use path signatures in approximate Bayesian computation to handle the sequential nature of time series. |
Joel Dyer; Patrick Cannon; Sebastian M. Schmon; |
| 2024 | 10 | End-to-end Conditional Robust Optimization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recently, a risk sensitive variant of CO, known as Conditional Robust Optimization (CRO), combines uncertainty quantification with robust optimization in order to promote safety and reliability in high stake applications. Exploiting modern differentiable optimization methods, we propose a novel end-to-end approach to train a CRO model in a way that accounts for both the empirical risk of the prescribed decisions and the quality of conditional coverage of the contextual uncertainty set that supports them. |
Abhilash Reddy Chenreddy; Erick Delage; |
| 2024 | 11 | Label-wise Aleatoric and Epistemic Uncertainty Quantification IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. |
YUSUF SALE et. al. |
| 2024 | 12 | Targeted Reduction of Causal Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an information theoretic objective to learn TCR from interventional data of simulations, establish identifiability for continuous variables under shift interventions and present a practical algorithm for learning TCRs. |
Armin Kekic; Bernhard Sch�lkopf; Michel Besserve; |
| 2024 | 13 | Polynomial Semantics of Tractable Probabilistic Circuits IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The relationships between these polynomial encodings of distributions is largely unknown. In this paper, we prove that for binary distributions, each of these probabilistic circuit models is equivalent in the sense that any circuit for one of them can be transformed into a circuit for any of the others with only a polynomial increase in size. |
Oliver Broadrick; Honghua Zhang; Guy Van den Broeck; |
| 2024 | 14 | Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce an innovative framework, Diffusion Ensembles for Capturing Uncertainty (DECU), designed for estimating epistemic uncertainty for diffusion models. |
Lucas Berry; Axel Brando; David Meger; |
| 2024 | 15 | Revisiting Convergence of AdaGrad with Relaxed Assumptions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we revisit the convergence of AdaGrad with momentum (covering AdaGrad as a special case) on non-convex smooth optimization problems. |
Yusu Hong; Junhong Lin; |
| 2023 | 1 | Jana: Jointly Amortized Neural Approximation of Complex Bayesian Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work proposes “jointly amortized neural approximation” (JANA) of intractable likelihood functions and posterior densities arising in Bayesian surrogate modeling and simulation-based inference. |
STEFAN T. RADEV et. al. |
| 2023 | 2 | Learning To Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These defenses have so far been very effective, in particular those based on gradient compression that allow the model to maintain high accuracy while greatly reducing the effectiveness of attacks. In this work, we argue that such findings underestimate the privacy risk in FL. |
Ruihan Wu; Xiangyu Chen; Chuan Guo; Kilian Q. Weinberger; |
| 2023 | 3 | Stochastic Generative Flow Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with stochastic dynamics, which can limit their applicability. To overcome this challenge, this paper introduces Stochastic GFlowNets, a new algorithm that extends GFlowNets to stochastic environments. |
Ling Pan; Dinghuai Zhang; Moksh Jain; Longbo Huang; Yoshua Bengio; |
| 2023 | 4 | Is The Volume of A Credal Set A Good Measure for Epistemic Uncertainty? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that the volume of the geometric representation of a credal set is a meaningful measure of epistemic uncertainty in the case of binary classification, but less so for multi-class classification. |
Yusuf Sale; Michele Caprio; Eyke H�llermeier; |
| 2023 | 5 | BISCUIT: Causal Representation Learning from Binary Interactions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that causal variables can still be identified for many common setups, e.g., additive Gaussian noise models, if the agent’s interactions with a causal variable can be described by an unknown binary variable. |
PHILLIP LIPPE et. al. |
| 2023 | 6 | Efficient Privacy-Preserving Stochastic Nonconvex Optimization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We study nonconvex ERM, which takes the form of minimizing a finite-sum of nonconvex loss functions over a training set. We propose a new differentially private stochastic gradient descent algorithm for nonconvex ERM that achieves strong privacy guarantees efficiently, and provide a tight analysis of its privacy and utility guarantees, as well as its gradient complexity. |
Lingxiao Wang; Bargav Jayaraman; David Evans; Quanquan Gu; |
| 2023 | 7 | Neural Probabilistic Logic Programming in Discrete-continuous Domains IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Hence, we introduce DeepSeaProbLog, a neural probabilistic logic programming language that incorporates DPP techniques into NeSy. |
LENNERT DE SMET et. al. |
| 2023 | 8 | Probabilistically Robust Conformal Prediction IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel adaptive PRCP (aPRCP) algorithm to achieve probabilistically robust coverage. |
SUBHANKAR GHOSH et. al. |
| 2023 | 9 | SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we show the benefits of using unstructured weight sparsity to train only a subset of weights during pre-training (Sparse Pre-training) and then recover the representational capacity by allowing the zeroed weights to learn (Dense Fine-tuning). |
VITHURSAN THANGARASA et. al. |
| 2023 | 10 | Approximate Thompson Sampling Via Epistemic Neural Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We compare a range of ENNs through computational experiments that assess their performance in approximating TS across bandit and reinforcement learning environments. |
IAN OSBAND et. al. |
| 2023 | 11 | Causal Discovery for Time Series from Multiple Datasets with Latent Contexts IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Pooling the datasets and considering the joint causal graph among system, context, and certain auxiliary variables enables us to overcome such latent confounding of system variables. In this work, we present a non-parametric time series causal discovery method, J(oint)-PCMCI$^+$, that efficiently learns such joint causal time series graphs when both observed and latent contexts are present, including time lags. |
Wiebke G�nther; Urmi Ninad; Jakob Runge; |
| 2023 | 12 | Random Reshuffling with Variance Reduction: New Analysis and Better Rates IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by these results, we seek to further improve the rates of shuffling-based methods. In particular, we show that it is possible to enhance them with a variance reduction mechanism, obtaining linear convergence rates. |
Grigory Malinovsky; Alibek Sailanbayev; Peter Richt�rik; |
| 2023 | 13 | CrysMMNet: Multimodal Representation for Crystal Property Prediction IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we leverage textual descriptions of materials to model global structural information into graph structure and learn a more robust and enriched representation of crystalline materials. |
Kishalay Das; Pawan Goyal; Seung-Cheol Lee; Satadeep Bhattacharjee; Niloy Ganguly; |
| 2023 | 14 | On The Informativeness of Supervision Signals IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We use information theory to compare how a number of commonly-used supervision signals contribute to representation-learning performance, as well as how their capacity is affected by factors such as the number of labels, classes, dimensions, and noise. |
ILIA SUCHOLUTSKY et. al. |
| 2023 | 15 | Mitigating Transformer Overconfidence Via Lipschitz Regularization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Though Transformers have achieved promising results in many computer vision tasks, they tend to be over-confident in predictions, as the standard Dot Product Self-Attention (DPSA) can barely preserve distance for the unbounded input domain. In this work, we fill this gap by proposing a novel Lipschitz Regularized Transformer (LRFormer). |
Wenqian Ye; Yunsheng Ma; Xu Cao; Kun Tang; |
| 2022 | 1 | Bayesian Structure Learning with Generative Flow Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose to use a GFlowNet as an alternative to MCMC for approximating the posterior distribution over the structure of Bayesian networks, given a dataset of observations. |
TRISTAN DELEU et. al. |
| 2022 | 2 | Multi-objective Bayesian Optimization Over High-dimensional Search Spaces IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work we propose MORBO, a scalable method for multi-objective BO over high-dimensional search spaces. |
Samuel Daulton; David Eriksson; Maximilian Balandat; Eytan Bakshy; |
| 2022 | 3 | On The Effectiveness of Adversarial Training Against Common Corruptions IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Then we explain why adversarial training performs better than data augmentation with simple Gaussian noise which has been observed to be a meaningful baseline on common corruptions. Related to this, we identify the sigma-overfitting phenomenon when Gaussian augmentation overfits to a particular standard deviation used for training which has a significant detrimental effect on common corruption accuracy. |
Klim Kireev; Maksym Andriushchenko; Nicolas Flammarion; |
| 2022 | 4 | Faster Non-convex Federated Learning Via Global and Local Momentum IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose \texttt{FedGLOMO}, a novel federated learning (FL) algorithm with an iteration complexity of $\mathcal{O}(\epsilon^{-1.5})$ to converge to an $\epsilon$-stationary point (i.e., $\mathbb{E}[\|\nabla f(x)\|^2] \leq \epsilon$) for smooth non-convex functions – under arbitrary client heterogeneity and compressed communication – compared to the $\mathcal{O}(\epsilon^{-2})$ complexity of most prior works. |
RUDRAJIT DAS et. al. |
| 2022 | 5 | Fedvarp: Tackling The Variance Due to Partial Client Participation in Federated Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We find that among these, only the former has received significant attention in the literature. To remedy this, we propose FedVARP, a novel variance reduction algorithm applied at the server that eliminates error due to partial client participation. |
Divyansh Jhunjhunwala; Pranay Sharma; Aushim Nagarkatti; Gauri Joshi; |
| 2022 | 6 | Greedy Relaxations of The Sparsest Permutation Algorithm IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We extend the methods of the latter by a permutation-based operation tuck, and develop a class of algorithms, namely GRaSP, that are computationally efficient and pointwise consistent under increasingly weaker assumptions than faithfulness. |
Wai-Yin Lam; Bryan Andrews; Joseph Ramsey; |
| 2022 | 7 | Quantification of Credal Uncertainty in Machine Learning: A Critical Analysis and Empirical Comparison IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we elaborate on uncertainty measures for credal sets from the perspective of machine learning. |
Eyke H�llermeier; S�bastien Destercke; Mohammad Hossein Shaker; |
| 2022 | 8 | Data Augmentation in Bayesian Neural Networks and The Cold Posterior Effect IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a “finite orbit” setting which allows valid likelihoods to be computed exactly, and for the more usual “full orbit” setting we derive multi-sample bounds tighter than those used previously. |
SETH NABARRO et. al. |
| 2022 | 9 | Calibrated Ensembles Can Mitigate Accuracy Tradeoffs Under Distribution Shift IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we find that a simple approach of ensembling the standard and robust models, after calibrating on only ID data, outperforms prior state-of-the-art both ID and OOD. |
Ananya Kumar; Tengyu Ma; Percy Liang; Aditi Raghunathan; |
| 2022 | 10 | Data Dependent Randomized Smoothing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we revisit Gaussian randomized smoothing and show that the variance of the Gaussian distribution can be optimized at each input so as to maximize the certification radius for the construction of the smooth classifier. |
Motasem Alfarra; Adel Bibi; Philip H. S. Torr; Bernard Ghanem; |
| 2022 | 11 | Stability of SGD: Tightness Analysis and Improved Bounds IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Stochastic Gradient Descent (SGD) based methods have been widely used for training large-scale machine learning models that also generalize well in practice. |
YIKAI ZHANG et. al. |
| 2022 | 12 | CounteRGAN: Generating Counterfactuals for Real-time Recourse and Interpretability Using Residual GANs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Model interpretability, fairness, and recourse for end users have increased as machine learning models have become increasingly popular in areas including criminal justice, finance, healthcare, and job marketplaces. This work presents a novel method of addressing these issues by producing meaningful counterfactuals that are aimed at providing recourse to users and highlighting potential model biases. |
Daniel Nemirovsky; Nicolas Thiebaut; Ye Xu; Abhishek Gupta; |
| 2022 | 13 | Fast Predictive Uncertainty for Classification with Bayesian Deep Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We analyze those and suggest a simple solution that compares favorably to other commonly used estimates of the softmax-Gaussian integral. |
Marius Hobbhahn; Agustinus Kristiadi; Philipp Hennig; |
| 2022 | 14 | Offline Reinforcement Learning Under Value and Density-ratio Realizability: The Power of Gaps IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function approximators. |
Jinglin Chen; Nan Jiang; |
| 2022 | 15 | Multi-source Domain Adaptation Via Weighted Joint Distributions Optimal Transport IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most current approaches tackle this problem by searching for an embedding that is invariant across source and target domains, which corresponds to searching for a universal classifier that works well on all domains. In this paper, we address this problem from a new perspective: instead of crushing diversity of the source distributions, we exploit it to adapt better to the target distribution. |
Rosanna Turrisi; R�mi Flamary; Alain Rakotomamonjy; Massimiliano Pontil; |
| 2021 | 1 | ReZero Is All You Need: Fast Convergence at Large Depth IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We apply this technique to language modeling and find that we can easily train 120-layer Transformers. |
Thomas Bachlechner; Bodhisattwa Prasad Majumder; Henry Mao; Gary Cottrell; Julian McAuley; |
| 2021 | 2 | High-dimensional Bayesian Optimization with Sparse Axis-aligned Subspaces IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In an extensive suite of experiments comparing to existing methods for high-dimensional BO we demonstrate that our algorithm, Sparse Axis-Aligned Subspace BO (SAASBO), achieves excellent performance on several synthetic and real-world problems without the need to set problem-specific hyperparameters. |
David Eriksson; Martin Jankowiak; |
| 2021 | 3 | Towards A Unified Framework for Fair and Stable Graph Representation Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we establish a key connection between counterfactual fairness and stability and leverage it to propose a novel framework, NIFTY (uNIfying Fairness and stabiliTY), which can be used with any GNN to learn fair and stable representations. |
Chirag Agarwal; Himabindu Lakkaraju; Marinka Zitnik; |
| 2021 | 4 | BayLIME: Bayesian Local Interpretable Model-agnostic Explanations IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches in XAI – which we call BayLIME. |
Xingyu Zhao; Wei Huang; Xiaowei Huang; Valentin Robu; David Flynn; |
| 2021 | 5 | The Promises and Pitfalls of Deep Kernel Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, we identify pathological behavior, including overfitting, on a simple toy example. We explore this pathology, explaining its origins and considering how it applies to real datasets. |
Sebastian W. Ober; Carl E. Rasmussen; Mark van der Wilk; |
| 2021 | 6 | TreeBERT: A Tree-based Pre-trained Model for Programming Language IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks. |
Xue Jiang; Zhuoran Zheng; Chen Lyu; Liang Li; Lei Lyu; |
| 2021 | 7 | Distribution-free Uncertainty Quantification for Classification Under Label Shift IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Piggybacking on recent progress in addressing label shift (for better prediction), we examine the right way to achieve UQ by reweighting the aforementioned conformal and calibration procedures whenever some unlabeled data from the target distribution is available. We examine these techniques theoretically in a distribution-free framework and demonstrate their excellent practical performance. |
Aleksandr Podkopaev; Aaditya Ramdas; |
| 2021 | 8 | Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our work, we introduce a new symmetric integration scheme for split HMC that does not rely on stochastic gradients. |
Adam D. Cobb; Brian Jalaian; |
| 2021 | 9 | Natural Language Adversarial Defense Through Synonym Encoding IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Especially, there exists few effective defense method against the successful synonym substitution based attacks that preserve the syntactic structure and semantic information of the original text while fooling the deep learning models. We contribute in this direction and propose a novel adversarial defense method called Synonym Encoding Method (SEM). |
Xiaosen Wang; Jin Hao; Yichen Yang; Kun He; |
| 2021 | 10 | The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To mitigate this issue, it is commonly believed that more training data will eventually help such adversarially robust models generalize better on the benign/unperturbed test data. In this paper, however, we challenge this conventional belief and show that more training data can hurt the generalization of adversarially robust models in classification problems. |
Yifei Min; Lin Chen; Amin Karbasi; |
| 2021 | 11 | Local Explanations Via Necessity and Sufficiency: Unifying Theory and Practice IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We provide a sound and complete algorithm for computing explanatory factors with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on various tasks. |
David S. Watson; Limor Gultchin; Ankur Taly; Luciano Floridi; |
| 2021 | 12 | The Complexity of Nonconvex-strongly-concave Minimax Optimization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our result reveals substantial gaps between these limits and best-known upper bounds in the literature. To close these gaps, we introduce a generic acceleration scheme that deploys existing gradient-based methods to solve a sequence of crafted strongly-convex-strongly-concave subproblems. |
Siqi Zhang; Junchi Yang; Crist�bal Guzm�n; Negar Kiyavash; Niao He; |
| 2021 | 13 | Measuring Data Leakage in Machine-learning Models with Fisher Information IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, when the training data contains sensitive attributes, assessing the amount of information leakage is paramount. We propose a method to quantify this leakage using the Fisher information of the model about the data. |
Awni Hannun; Chuan Guo; Laurens van der Maaten; |
| 2021 | 14 | Trumpets: Injective Flows for Inference and Inverse Problems IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose injective generative models called Trumpets that generalize invertible normalizing flows. |
Konik Kothari; AmirEhsan Khorashadizadeh; Maarten de Hoop; Ivan Dokmanic; |
| 2021 | 15 | Sketching Curvature for Efficient Out-of-distribution Detection for Deep Neural Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on recent work leveraging the local curvature of DNNs to reason about epistemic uncertainty, we propose Sketching Curvature for OoD Detection (SCOD), an architecture-agnostic framework for equipping any trained DNN with a task-relevant epistemic uncertainty estimate. |
Apoorva Sharma; Navid Azizan; Marco Pavone; |
| 2020 | 1 | Discovering Contemporaneous And Lagged Causal Relations In Autocorrelated Nonlinear Time Series Datasets IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The paper introduces a novel conditional independence (CI) based method for linear and nonlinear, lagged and contemporaneous causal discovery from observational time series in the causally sufficient case. |
Jakob Runge; |
| 2020 | 2 | Adapting Text Embeddings For Causal Inference IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper develops a method to estimate such causal effects from observational text data, adjusting for confounding features of the text such as the subject or writing quality. |
Victor Veitch; Dhanya Sridhar; David Blei; |
| 2020 | 3 | On Counterfactual Explanations Under Predictive Multiplicity IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we derive a general upper bound for the costs of counterfactual explanations under predictive multiplicity. |
Martin Pawelczyk; Klaus Broelemann; Gjergji. Kasneci; |
| 2020 | 4 | Permutation-Based Causal Structure Learning With Unknown Intervention Targets IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We consider the problem of estimating causal DAG models from a mix of observational and interventional data, when the intervention targets are partially or completely unknown. |
Chandler Squires; Yuhao Wang; Caroline Uhler; |
| 2020 | 5 | Greedy Policy Search: A Simple Baseline For Learnable Test-Time Augmentation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The primary goal of this paper is to demonstrate that test-time augmentation policies can be successfully learned too. |
Alexander Lyzhov; Yuliya Molchanova; Arsenii Ashukha; Dmitry Molchanov; Dmitry Vetrov; |
| 2020 | 6 | Q* Approximation Schemes For Batch Reinforcement Learning: A Theoretical Comparison IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We prove performance guarantees of two algorithms for approximating Q* in batch reinforcement learning. |
Tengyang Xie; Nan Jiang; |
| 2020 | 7 | Dueling Posterior Sampling For Preference-Based Reinforcement Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building upon ideas from preference-based bandit learning and posterior sampling in RL, we present DUELING POSTERIOR SAMPLING (DPS), which employs preference-based posterior sampling to learn both the system dynamics and the underlying utility function that governs the preference feedback. |
Ellen Novoseller; Yibing Wei; Yanan Sui; Yisong Yue; Joel Burdick; |
| 2020 | 8 | Verifying Individual Fairness In Machine Learning Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our objective is to construct verifiers for proving individual fairness of a given model, and we do so by considering appropriate relaxations of the problem. |
Philips George John; Deepak Vijaykeerthy; Diptikalyan Saha; |
| 2020 | 9 | Fair Contextual Multi-Armed Bandits: Theory And Experiments IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a Multi-Armed Bandit algorithm with fairness constraints, where fairness is defined as a minimum rate at which a task or a resource is assigned to a user. |
YIFANG CHEN et. al. |
| 2020 | 10 | Regret Analysis Of Bandit Problems With Causal Background Knowledge IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose two algorithms, causal upper confidence bound (C-UCB) and causal Thompson Sampling (C-TS), that enjoy improved cumulative regret bounds compared with algorithms that do not use causal information. |
Yangyi Lu; Amirhossein Meisami; Ambuj Tewari; William Yan; |
| 2020 | 11 | Probabilistic Safety For Bayesian Neural Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We apply our methods to BNNs trained on a regression task, airborne collision avoidance, and MNIST, empirically showing that our approach allows one to certify probabilistic safety of BNNs with millions of parameters. |
Matthew Wicker; Luca Laurenti; Andrea Patane; Marta Kwiatkowska; |
| 2020 | 12 | Lagrangian Decomposition For Neural Network Verification IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel approach based on Lagrangian Decomposition. |
RUDY BUNEL et. al. |
| 2020 | 13 | Constraint-Based Causal Discovery Using Partial Ancestral Graphs In The Presence Of Cycles IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we show that—surprisingly—the output of the Fast Causal Inference (FCI) algorithm is correct if it is applied to observational data generated by a system that involves feedback. |
Joris M. Mooij; Tom Claassen; |
| 2020 | 14 | Neural Likelihoods Via Cumulative Distribution Functions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We leverage neural networks as universal approximators of monotonic functions to build a parameterization of conditional cumulative distribution functions (CDFs). |
Pawel Chilinski; Ricardo Silva; |
| 2020 | 15 | Identifying Causal Effects In Maximally Oriented Partially Directed Acyclic Graphs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We develop a necessary and sufficient causal identification criterion for maximally oriented partially directed acyclic graphs (MPDAGs). |
Emilija Perkovic; |
| 2019 | 1 | Random Search And Reproducibility For Neural Architecture Search IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) NAS is a specialized hyperparameter optimization problem; and (ii) random search is a competitive baseline for hyperparameter optimization. |
Liam Li; Ameet Talwalkar; |
| 2019 | 2 | Sliced Score Matching: A Scalable Approach To Density And Score Estimation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We show this difficulty can be mitigated by projecting the scores onto random vectors before comparing them. |
Yang Song; Sahaj Garg; Jiaxin Shi; Stefano Ermon; |
| 2019 | 3 | Fall Of Empires: Breaking Byzantine-tolerant SGD By Inner Product Manipulation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we break two prevailing Byzantine-tolerant techniques. |
Cong Xie; Oluwasanmi Koyejo; Indranil Gupta; |
| 2019 | 4 | N-GCN: Multi-scale Graph Convolution For Semi-supervised Node Classification IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a model: Network of GCNs (N-GCN), which marries these two lines of work. |
Sami Abu-El-Haija; Amol Kapoor; Bryan Perozzi; Joonseok Lee; |
| 2019 | 5 | Wasserstein Fair Classification IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an approach to fair classification that enforces independence between the classifier outputs and sensitive information by minimizing Wasserstein-1 distances. |
Ray Jiang; Aldo Pacchiano; Tom Stepleton; Heinrich Jiang; Silvia Chiappa; |
| 2019 | 6 | Low Frequency Adversarial Perturbation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we propose to restrict the search for adversarial images to a low frequency domain. |
Chuan Guo; Jared S. Frank; Kilian Q. Weinberger; |
| 2019 | 7 | Truly Proximal Policy Optimization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that PPO could neither strictly restrict the probability ratio as it attempts to do nor enforce a well-defined trust region constraint, which means that it may still suffer from the risk of performance instability. |
Yuhui Wang; Hao He; Xiaoyang Tan; |
| 2019 | 8 | A Fast Proximal Point Method For Computing Exact Wasserstein Distance IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. |
Yujia Xie; Xiangfeng Wang; Ruijia Wang; Hongyuan Zha; |
| 2019 | 9 | A Flexible Framework For Multi-Objective Bayesian Optimization Using Random Scalarizations IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a strategy based on random scalarizations of the objectives that addresses this problem. |
Biswajit Paria; Kirthevasan Kandasamy; Barnab�s P�czos; |
| 2019 | 10 | Subspace Inference For Bayesian Deep Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. |
PAVEL IZMAILOV et. al. |
| 2019 | 11 | Practical Multi-fidelity Bayesian Optimization For Hyperparameter Tuning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a highly flexible and practical approach to multi-fidelity Bayesian optimization, focused on efficiently optimizing hyperparameters for iteratively trained supervised learning models. |
Jian Wu; Saul Toscano-Palmerin; Peter I. Frazier; Andrew Gordon Wilson; |
| 2019 | 12 | Block Neural Autoregressive Flow IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose block neural autoregressive flow (B-NAF), a much more compact universal approximator of density functions, where we model a bijection directly using a single feed-forward network. |
Nicola De Cao; Wilker Aziz; Ivan Titov; |
| 2019 | 13 | Deep Mixture Of Experts Via Shallow Embedding IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We explore a mixture of experts (MoE) approach to deep dynamic routing, which activates certain experts in the network on a per-example basis. |
XIN WANG et. al. |
| 2019 | 14 | Random Sum-Product Networks: A Simple And Effective Approach To Probabilistic Deep Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we follow a simple “deep learning” approach, by generating unspecialized random structures, scalable to millions of parameters, and subsequently applying GPU-based optimization. |
ROBERT PEHARZ et. al. |
| 2019 | 15 | Domain Generalization Via Multidomain Discriminant Analysis IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Multidomain Discriminant Analysis (MDA) to address DG of classification tasks in general situations. |
Shoubo Hu; Kun Zhang; Zhitang Chen; Laiwan Chan; |