Robust hypothesis testing and distribution estimation in Hellinger distance
Statistics Theory
2020-11-04 v1 Information Theory
Machine Learning
math.IT
Machine Learning
Statistics Theory
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.
Keywords
Cite
@article{arxiv.2011.01848,
title = {Robust hypothesis testing and distribution estimation in Hellinger distance},
author = {Ananda Theertha Suresh},
journal= {arXiv preprint arXiv:2011.01848},
year = {2020}
}