Stability of adversarial Markov chains, with an application to adaptive MCMC algorithms
Probability
2016-08-11 v4
Abstract
We consider whether ergodic Markov chains with bounded step size remain bounded in probability when their transitions are modified by an adversary on a bounded subset. We provide counterexamples to show that the answer is no in general, and prove theorems to show that the answer is yes under various additional assumptions. We then use our results to prove convergence of various adaptive Markov chain Monte Carlo algorithms.
Cite
@article{arxiv.1403.3950,
title = {Stability of adversarial Markov chains, with an application to adaptive MCMC algorithms},
author = {Radu V. Craiu and Lawrence Gray and Krzysztof Łatuszyński and Neal Madras and Gareth O. Roberts and Jeffrey S. Rosenthal},
journal= {arXiv preprint arXiv:1403.3950},
year = {2016}
}
Comments
Published at http://dx.doi.org/10.1214/14-AAP1083 in the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)