Subgeometric rates of convergence in Wasserstein distance for Markov chains

DOI10.1214/15-AIHP699zbMath1355.60096arXiv1402.4577OpenAlexW2963365836MaRDI QIDQ503093

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)

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

zbMATH Keywords

Markov chainsMarkov chain Monte Carlo methodWasserstein distancesubgeometric ergodicity

Mathematics Subject Classification ID

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

Related Items (13)

Quantitative contraction rates for Markov chains on general state spaces ⋮ Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric ⋮ Quantitative spectral gaps for hypoelliptic stochastic differential equations with small noise ⋮ Generalized couplings and ergodic rates for SPDEs and other Markov models ⋮ Subexponential upper and lower bounds in Wasserstein distance for Markov processes ⋮ Polynomial mixing of a stochastic wave equation with dissipative damping ⋮ Well-posedness, stability and sensitivities for stochastic delay equations: a generalized coupling approach ⋮ On sub-geometric ergodicity of diffusion processes ⋮ Ergodicity of a Lévy-driven SDE arising from multiclass many-server queues ⋮ On the convergence of formally diverging neural net-based classifiers ⋮ Convergence rates of symmetric scan Gibbs sampler ⋮ Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions ⋮ Stability for the training of deep neural networks and other classifiers

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