AISTATS 2019poster269 citations

Does data interpolation contradict statistical optimality?

Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov

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.

BibTeX
@InProceedings{pmlr-v89-belkin19a,
  title = 	 {Does data interpolation contradict statistical optimality?},
  author =       {Belkin, Mikhail and Rakhlin, Alexander and Tsybakov, Alexandre B.},
  booktitle = 	 {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1611--1619},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Sugiyama, Masashi},
  volume = 	 {89},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {16--18 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v89/belkin19a/belkin19a.pdf},
  url = 	 {https://proceedings.mlr.press/v89/belkin19a.html},
  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.}
}
Does data interpolation contradict statistical optimality? · AISTATS 2019