Subgeometric rates of convergence in Wasserstein distance for Markov chains

DOI10.1214/15-AIHP699zbMATH Open1355.60096arXiv1402.4577OpenAlexW2963365836MaRDI QIDQ503093FDOQ503093

Authors: Alain Durmus, Gersende Fort, Eric Moulines 

Publication date: 11 January 2017

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Abstract: In this paper, we provide sufficient conditions for the existence of the invariant distribution and for subgeometric rates of convergence in Wasserstein distance for general state-space Markov chains which are (possibly) not irreducible. Compared to previous work, our approach is based on a purely probabilistic coupling construction which allows to retrieve rates of convergence matching those previously reported for convergence in total variation. Our results are applied to establish the subgeometric ergodicity in Wasserstein distance of non-linear autoregressive models and of the pre-conditioned Crank-Nicolson Markov chain Monte Carlo algorithm in Hilbert space.

Full work available at URL: https://arxiv.org/abs/1402.4577

Recommendations

• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• Subexponential upper and lower bounds in Wasserstein distance for Markov processes
• Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
• Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions
• Quantitative convergence rates for subgeometric Markov chains
• Wasserstein convergence rates for random bit approximations of continuous Markov processes
• Subgeometric rates of convergence for Markov processes under subordination
• Subgeometric rates of convergence for a class of continuous-time Markov process

zbMATH Keywords

Wasserstein distanceMarkov chain Monte Carlo methodMarkov chainssubgeometric ergodicity

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Central limit and other weak theorems (60F05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Discrete-time Markov processes on general state spaces (60J05)

Cited In (25)

• Generalized Wasserstein distance and weak convergence of sublinear expectations
• Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric
• Polynomial mixing of a stochastic wave equation with dissipative damping
• Wasserstein convergence rates for empirical measures of subordinated processes on noncompact manifolds
• Quantitative convergence rates for subgeometric Markov chains
• Ergodicity of a Lévy-driven SDE arising from multiclass many-server queues
• Well-posedness, stability and sensitivities for stochastic delay equations: a generalized coupling approach
• Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions
• Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
• Generalized couplings and ergodic rates for SPDEs and other Markov models
• On the convergence of formally diverging neural net-based classifiers
• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• Stability for the training of deep neural networks and other classifiers
• Subexponential upper and lower bounds in Wasserstein distance for Markov processes
• Mixing of Metropolis-adjusted Markov chains via couplings: the high acceptance regime
• Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration
• Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
• Quantitative spectral gaps for hypoelliptic stochastic differential equations with small noise
• Convergence rates of symmetric scan Gibbs sampler
• Convergence rates of Metropolis-Hastings algorithms
• Prokhorov Distance with Rates of Convergence under Sublinear Expectations
• Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm
• On sub-geometric ergodicity of diffusion processes
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
• Quantitative contraction rates for Markov chains on general state spaces

This page was built for publication: Subgeometric rates of convergence in Wasserstein distance for Markov chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q503093)