Most Influential AISTATS 2019 Paper · 2026-03 edition
Does Data Interpolation Contradict Statistical Optimality?
Mikhail Belkin; Alexander Rakhlin; Alexandre B. Tsybakov
Venue
Conference on Artificial Intelligence and Statistics (AISTATS) 2019
Recognition
Most Influential AISTATS 2019 Paper (Rank No. 12)
Edition
2026-03
Impact factor
5
Certificate ID
7c646751ae101ac5
Abstract
We show that classical learning methods interpolating the training data can achieve optimal rates for the problems of nonparametric regression and prediction with square loss.