A quantitative Mc Diarmid's inequality for geometrically ergodic Markov chains

2019/07/05 by Antoine Havet, Matthieu Lerasle, Havet, Antoine +5 · 1 citation
Mathematics · #Markov Chains and Monte Carlo Methods #Stochastic processes and statistical mechanics #Graph theory and applications

paper · pdf · doi:10.48550/arxiv.1907.02809

Abstract

We state and prove a quantitative version of the bounded difference inequality for geometrically ergodic Markov chains. Our proof uses the same martingale decomposition as \citeMR3407208 but, compared to this paper, the exact coupling argument is modified to fill a gap between the strongly aperiodic case and the general aperiodic case.

Cited by

• Variance reduction for Markov chains with application to MCMC

Related

• Subgaussian concentration inequalities for geometrically ergodic Markov chains
• Equivalences of Geometric Ergodicity of Markov Chains
• Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms
• Geometric Ergodicity and Perfect Simulation
• Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains