Does Data Interpolation Contradict Statistical Optimality?

Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov

AISTATS 2019 pp. 1611-1619

/aistats/2019/belkin2019aistats-data/

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.

PDF AISTATS Semantic Scholar

Cite

Text

Belkin et al. "Does Data Interpolation Contradict Statistical Optimality?." Artificial Intelligence and Statistics, 2019.

Markdown

[Belkin et al. "Does Data Interpolation Contradict Statistical Optimality?." Artificial Intelligence and Statistics, 2019.](https://mlanthology.org/aistats/2019/belkin2019aistats-data/)

BibTeX

@inproceedings{belkin2019aistats-data,
  title     = {{Does Data Interpolation Contradict Statistical Optimality?}},
  author    = {Belkin, Mikhail and Rakhlin, Alexander and Tsybakov, Alexandre B.},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2019},
  pages     = {1611-1619},
  volume    = {89},
  url       = {https://mlanthology.org/aistats/2019/belkin2019aistats-data/}
}