A Geometric Reduction Approach for Identity Testing of Reversible Markov Chains
Probability
2023-02-17 v1 Information Theory
math.IT
Machine Learning
Abstract
We consider the problem of testing the identity of a reversible Markov chain against a reference from a single trajectory of observations. Employing the recently introduced notion of a lumping-congruent Markov embedding, we show that, at least in a mildly restricted setting, testing identity to a reversible chain reduces to testing to a symmetric chain over a larger state space and recover state-of-the-art sample complexity for the problem.
Cite
@article{arxiv.2302.08059,
title = {A Geometric Reduction Approach for Identity Testing of Reversible Markov Chains},
author = {Geoffrey Wolfer and Shun Watanabe},
journal= {arXiv preprint arXiv:2302.08059},
year = {2023}
}