Subgaussian concentration inequalities for geometrically ergodic Markov chains

2014/12/04 by Jérôme Dedecker, Dedecker, Jérôme, Sébastien Gouëzel +1 · 1 citation
Mathematics · #FOS: Mathematics #Graph theory and applications #Markov Chains and Monte Carlo Methods #Probability (math.PR) #Stochastic processes and statistical mechanics #math.PR

paper · pdf · doi:10.48550/arxiv.1412.1794

openalex publication_date 2014/12/04 · arxiv created 2015/07/21 · arxiv updated 2015/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We prove that an irreducible aperiodic Markov chain is geometrically ergodic if and only if any separately bounded functional of the stationary chain satisfies an appropriate subgaussian deviation inequality from its mean.

Cited by

• Ergodicity of Approximate MCMC Chains with Applications to Large Data Sets
• Convergence rate of Euler-Maruyama scheme to the invariant probability measure under total variation distance

Related

• A quantitative Mc Diarmid's inequality for geometrically ergodic Markov chains
• Equivalences of Geometric Ergodicity of Markov Chains
• Uniform Chernoff and Dvoretzky-Kiefer-Wolfowitz-type inequalities for Markov chains and related processes
• Geometric ergodicity for families of homogeneous Markov chains
• Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms