Robust hypothesis testing and distribution estimation in Hellinger distance

Ananda Theertha Suresh
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2962-2970, 2021.

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 this Paper

BibTeX
@InProceedings{pmlr-v130-theertha-suresh21a, title = { Robust hypothesis testing and distribution estimation in Hellinger distance }, author = {Theertha Suresh, Ananda}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {2962--2970}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/theertha-suresh21a/theertha-suresh21a.pdf}, url = {https://proceedings.mlr.press/v130/theertha-suresh21a.html}, 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. } }
Endnote
%0 Conference Paper %T Robust hypothesis testing and distribution estimation in Hellinger distance %A Ananda Theertha Suresh %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-theertha-suresh21a %I PMLR %P 2962--2970 %U https://proceedings.mlr.press/v130/theertha-suresh21a.html %V 130 %X 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.
APA
Theertha Suresh, A.. (2021). Robust hypothesis testing and distribution estimation in Hellinger distance . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:2962-2970 Available from https://proceedings.mlr.press/v130/theertha-suresh21a.html.

Related Material