On geometric convergence for the Metropolis-adjusted Langevin algorithm under simple conditions - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Biometrika Année : 2023

On geometric convergence for the Metropolis-adjusted Langevin algorithm under simple conditions

Résumé

Summary While the Metropolis-adjusted Langevin algorithm is a popular and widely used Markov chain Monte Carlo method, very few papers derive conditions that ensure its convergence. In particular, to the authors’ knowledge, assumptions that are both easy to verify and guarantee geometric convergence, are still missing. In this work, we establish V-uniformly geometric convergence for the Metropolis-adjusted Langevin algorithm under mild assumptions about the target distribution. Unlike previous work, we only consider tail and smoothness conditions for the potential associated with the target distribution. These conditions are quite common in the Markov chain Monte Carlo literature. Finally, we pay special attention to the dependence of the bounds we derive on the step size of the Euler–Maruyama discretization, which corresponds to the proposed Markov kernel of the Metropolis-adjusted Langevin algorithm.

Domaines

Calcul [stat.CO]
Fichier non déposé

Dates et versions

hal-04549966 , version 1 (17-04-2024)

Identifiants

Citer

Alain Oliviero-Durmus, Éric Moulines. On geometric convergence for the Metropolis-adjusted Langevin algorithm under simple conditions. Biometrika, In press, ⟨10.1093/biomet/asad060⟩. ⟨hal-04549966⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More