← Back to papers
2019 AISTATS AISTATS 2019

Does data interpolation contradict statistical optimality?

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.

❓ The Questioner
🧭 Keyword Pioneer — data interpolation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Machine Learning, Mathematics & Optimization, Reinforcement Learning, Robotics

Authors

Mikhail Belkin , Alexander Rakhlin , Alexandre B. Tsybakov

Topics

Machine Learning > Core Methods > Regression Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning

Keywords

nonparametric regression square loss statistical optimality data interpolation
Download PDF

Related papers

Inferring Multidimensional Rates of Aging from Cross-Sectional Data 2019
On the Interaction Effects Between Prediction and Clustering 2019
Efficient Linear Bandits through Matrix Sketching 2019
An Optimal Algorithm for Stochastic Three-Composite Optimization 2019
Efficient Inference in Multi-task Cox Process Models 2019