Subgaussian concentration inequalities for geometrically ergodic Markov chains

DOI10.1214/ECP.V20-3966zbMATH Open1329.60251arXiv1412.1794OpenAlexW1498640940MaRDI QIDQ894490FDOQ894490

Authors: S. Gouëzel, Jérôme Dedecker 

Publication date: 1 December 2015

Published in: Electronic Communications in Probability (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1412.1794

Recommendations

• Exponential concentration inequalities for additive functionals of Markov chains
• A quantitative McDiarmid's inequality for geometrically ergodic Markov chains
• Uniform Chernoff and Dvoretzky-Kiefer-Wolfowitz-type inequalities for Markov chains and related processes
• General Bernstein-like inequality for additive functionals of Markov chains
• Sharp bounds for the tails of functionals of Markov chains

zbMATH Keywords

Markov chainscouplinggeometric ergodicitysub-Gaussian concentration inequalities

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10)

Cited In (22)

• Sharp non-asymptotic concentration inequalities for the approximation of the invariant distribution of a diffusion
• Non-asymptotic Gaussian estimates for the recursive approximation of the invariant distribution of a diffusion
• Title not available (Why is that?)
• Fourier transform MCMC, heavy-tailed distributions, and geometric ergodicity
• Learning the distribution of latent variables in paired comparison models with round-robin scheduling
• Central limit theorem and self-normalized Cramér-type moderate deviation for Euler-Maruyama scheme
• A quantitative McDiarmid's inequality for geometrically ergodic Markov chains
• Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains
• A martingale minimax exponential inequality for Markov chains
• Deviation inequalities for separately Lipschitz functionals of composition of random functions
• Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
• Asymptotic optimality of isoperimetric constants
• Gaussian concentration bounds for stochastic chains of unbounded memory
• General Bernstein-like inequality for additive functionals of Markov chains
• Bounds on regeneration times and convergence rates for Markov chains
• Some recent advances in random walks and random environments
• (Non)-escape of mass and equidistribution for horospherical actions on trees
• Geometric inequalities for the eigenvalues of concentrated Markov chains
• Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms
• Non parametric estimation for random walks in random environment
• Adaptive invariant density estimation for continuous-time mixing Markov processes under sup-norm risk
• Random walks on hyperbolic spaces: concentration inequalities and probabilistic Tits alternative

This page was built for publication: Subgaussian concentration inequalities for geometrically ergodic Markov chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q894490)