On the Second-Order Asymptotics of the Hoeffding Test and Other Divergence Tests
Abstract
Consider a binary statistical hypothesis testing problem, where independent and identically distributed random variables are either distributed according to the null hypothesis or the alternative hypothesis , and only is known. A well-known test that is suitable for this case is the so-called Hoeffding test, which accepts if the Kullback-Leibler (KL) divergence between the empirical distribution of and is below some threshold. This work characterizes the first and second-order terms of the type-II error probability for a fixed type-I error probability for the Hoeffding test as well as for divergence tests, where the KL divergence is replaced by a general divergence. It is demonstrated that, irrespective of the divergence, divergence tests achieve the first-order term of the Neyman-Pearson test, which is the optimal test when both and are known. In contrast, the second-order term of divergence tests is strictly worse than that of the Neyman-Pearson test. It is further demonstrated that divergence tests with an invariant divergence achieve the same second-order term as the Hoeffding test, but divergence tests with a non-invariant divergence may outperform the Hoeffding test for some alternative hypotheses . Potentially, this behavior could be exploited by a composite hypothesis test with partial knowledge of the alternative hypothesis by tailoring the divergence of the divergence test to the set of possible alternative hypotheses.
Keywords
Cite
@article{arxiv.2403.03537,
title = {On the Second-Order Asymptotics of the Hoeffding Test and Other Divergence Tests},
author = {K. V. Harsha and Jithin Ravi and Tobias Koch},
journal= {arXiv preprint arXiv:2403.03537},
year = {2024}
}
Comments
Submitted to the IEEE Transactions on Information Theory