Robust Hypothesis Testing and Distribution Estimation in Hellinger Distance
Abstract
We propose a simple robust hypothesis test that has the same sample complexity as that of the optimal Neyman-Pearson test up to constants, but robust to distribution perturbations under Hellinger distance. We discuss the applicability of such a robust test for estimating distributions in Hellinger distance. We empirically demonstrate the power of the test on canonical distributions.
Cite
Text
Theertha Suresh. "Robust Hypothesis Testing and Distribution Estimation in Hellinger Distance." Artificial Intelligence and Statistics, 2021.Markdown
[Theertha Suresh. "Robust Hypothesis Testing and Distribution Estimation in Hellinger Distance." Artificial Intelligence and Statistics, 2021.](https://mlanthology.org/aistats/2021/theerthasuresh2021aistats-robust/)BibTeX
@inproceedings{theerthasuresh2021aistats-robust,
title = {{Robust Hypothesis Testing and Distribution Estimation in Hellinger Distance}},
author = {Theertha Suresh, Ananda},
booktitle = {Artificial Intelligence and Statistics},
year = {2021},
pages = {2962-2970},
volume = {130},
url = {https://mlanthology.org/aistats/2021/theerthasuresh2021aistats-robust/}
}