On the $\alpha$-lazy version of Markov chains in estimation and testing problems
Machine Learning
2021-11-02 v2 Machine Learning
Abstract
Given access to a single long trajectory generated by an unknown irreducible Markov chain , we simulate an -lazy version of which is ergodic. This enables us to generalize recent results on estimation and identity testing that were stated for ergodic Markov chains in a way that allows fully empirical inference. In particular, our approach shows that the pseudo spectral gap introduced by Paulin [2015] and defined for ergodic Markov chains may be given a meaning already in the case of irreducible but possibly periodic Markov chains.
Cite
@article{arxiv.2105.09536,
title = {On the $\alpha$-lazy version of Markov chains in estimation and testing problems},
author = {Sela Fried and Geoffrey Wolfer},
journal= {arXiv preprint arXiv:2105.09536},
year = {2021}
}