Does data interpolation contradict statistical optimality?

Research output: Contribution to journalConference articlepeer-review

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.

Original languageEnglish
Pages (from-to)1611-1619
Number of pages9
JournalProceedings of Machine Learning Research
Volume89
Publication statusPublished - 1 Jan 2019
Externally publishedYes
Event22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 - Naha, Japan
Duration: 16 Apr 201918 Apr 2019

Fingerprint

Dive into the research topics of 'Does data interpolation contradict statistical optimality?'. Together they form a unique fingerprint.

Cite this