Subgeometric rates of convergence in Wasserstein distance for Markov chains - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Subgeometric rates of convergence in Wasserstein distance for Markov chains

Résumé

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.
Fichier principal
Vignette du fichier
main.pdf (732.06 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00948661 , version 1 (18-02-2014)
hal-00948661 , version 2 (06-11-2014)
hal-00948661 , version 3 (10-07-2015)

Identifiants

Citer

Alain Durmus, Gersende Fort, Éric Moulines. Subgeometric rates of convergence in Wasserstein distance for Markov chains. 2015. ⟨hal-00948661v3⟩
321 Consultations
507 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More