Second-Order Asymptotics of Hoeffding-Like Hypothesis Tests
Abstract
We consider a binary statistical hypothesis testing problem, where independent and identically distributed random variables are either distributed according to the null hypothesis or the alternate hypothesis , and only is known. For this problem, a well-known test is the Hoeffding test, which accepts if the Kullback-Leibler (KL) divergence between the empirical distribution of and is below some threshold. In this paper, we consider Hoeffding-like tests, where the KL divergence is replaced by other divergences, and characterize, for a large class of divergences, the first and second-order terms of the type-II error for a fixed type-I error. Since the considered class includes the KL divergence, we obtain the second-order term of the Hoeffiding test as a special case.
Keywords
Cite
@article{arxiv.2205.05631,
title = {Second-Order Asymptotics of Hoeffding-Like Hypothesis Tests},
author = {K. V. Harsha and Jithin Ravi and Tobias Koch},
journal= {arXiv preprint arXiv:2205.05631},
year = {2022}
}
Comments
26 pages. Submitted to the 2022 IEEE Information Theory Workshop