Benign overfitting and adaptive nonparametric regression
Statistics Theory
2022-06-28 v1 Machine Learning
Machine Learning
Statistics Theory
Abstract
In the nonparametric regression setting, we construct an estimator which is a continuous function interpolating the data points with high probability, while attaining minimax optimal rates under mean squared risk on the scale of H\"older classes adaptively to the unknown smoothness.
Cite
@article{arxiv.2206.13347,
title = {Benign overfitting and adaptive nonparametric regression},
author = {Julien Chhor and Suzanne Sigalla and Alexandre B. Tsybakov},
journal= {arXiv preprint arXiv:2206.13347},
year = {2022}
}