We are experiencing some difficulties with our submission forms, which we are working to resolve. If you have any issues, please contact us at dspace-lib@mit.edu.

Does data interpolation contradict statistical optimality?

Thumbnail Image
Download
Name

belkin19a.pdf

Description
Published version
Size

479.21 KB

Format

Unknown

Checksum (MD5)

eae6a3100d8ef2f91170702e78463fec

sword-2021-12-03T15:12:02.original.xml (130 B)
Original SWORD entry document
Author(s)
Rakhlin, Alexander
Date Issued
April 1, 2019
Journal
AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics
Citation
Belkin, M, Rakhlin, A and Tsybakov, AB. 2020. "Does data interpolation contradict statistical optimality?." AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, 89.
Version
Final published version
Abstract
© 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.
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://proceedings.mlr.press/v89/belkin19a.html
PrivacyPermissionsAccessibilityContact us
Notify us about copyright concerns.