Does data interpolation contradict statistical optimality?

Does data interpolation contradict statistical optimality?

Show other versions (1)

© 2019 by the author(s). 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.

Bibliographic Details
Main Author: Rakhlin, Alexander (Author)
Format: Article
Language:English
Published: International Machine Learning Society, 2021-12-08T13:51:14Z.
Subjects:
Article
Online Access:Get fulltext
LEADER 00697 am a22001453u 4500
001 138307.3
042 |a dc 
100 1 0 |a Rakhlin, Alexander  |e author 
245 0 0 |a Does data interpolation contradict statistical optimality? 
260 |b International Machine Learning Society,   |c 2021-12-08T13:51:14Z. 
856 |z Get fulltext  |u https://hdl.handle.net/1721.1/138307.3 
520 |a © 2019 by the author(s). 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. 
546 |a en 
655 7 |a Article 
773 |t AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics 

Similar Items