Does data interpolation contradict statistical optimality?
DownloadPublished version (479.2Kb)
Publisher Policy
Publisher Policy
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.
Terms of use
Metadata
Show full item recordAbstract
© 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.
Date issued
2019-04-01Department
Massachusetts Institute of Technology. Department of Brain and Cognitive SciencesJournal
AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics
Publisher
International Machine Learning Society
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
ISSN
2640-3498