Does data interpolation contradict statistical optimality?

© 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
Other Authors: Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences.
Format: Article
Language:English
Published: 2021
Online Access:https://hdl.handle.net/1721.1/138307.2
_version_ 1811092640005881856
author Rakhlin, Alexander
author2 Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences.
author_facet Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences.
Rakhlin, Alexander
author_sort Rakhlin, Alexander
collection MIT
description © 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.
first_indexed 2024-09-23T15:21:17Z
format Article
id mit-1721.1/138307.2
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T15:21:17Z
publishDate 2021
record_format dspace
spelling mit-1721.1/138307.22021-12-06T13:42:50Z Does data interpolation contradict statistical optimality? Rakhlin, Alexander Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences. © 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. 2021-12-06T13:42:49Z 2021-12-03T15:23:42Z 2021-12-06T13:42:49Z 2019-04-01 2021-12-03T15:12:02Z Article http://purl.org/eprint/type/ConferencePaper 2640-3498 https://hdl.handle.net/1721.1/138307.2 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. en https://proceedings.mlr.press/v89/belkin19a.html AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics 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. application/octet-stream Proceedings of Machine Learning Research
spellingShingle Rakhlin, Alexander
Does data interpolation contradict statistical optimality?
title Does data interpolation contradict statistical optimality?
title_full Does data interpolation contradict statistical optimality?
title_fullStr Does data interpolation contradict statistical optimality?
title_full_unstemmed Does data interpolation contradict statistical optimality?
title_short Does data interpolation contradict statistical optimality?
title_sort does data interpolation contradict statistical optimality
url https://hdl.handle.net/1721.1/138307.2
work_keys_str_mv AT rakhlinalexander doesdatainterpolationcontradictstatisticaloptimality