DeepAI AI Chat
Log In Sign Up

On the geometric convergence for MALA under verifiable conditions

by   Alain Durmus, et al.

While the Metropolis Adjusted Langevin Algorithm (MALA) 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 MALA 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 MCMC literature and are easy to verify in practice. 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 proposal Markov kernel of MALA.


page 1

page 2

page 3

page 4


Boost your favorite Markov Chain Monte Carlo sampler using Kac's theorem: the Kick-Kac teleportation algorithm

The present paper focuses on the problem of sampling from a given target...

Convergence Speed and Approximation Accuracy of Numerical MCMC

When implementing Markov Chain Monte Carlo (MCMC) algorithms, perturbati...

On the use of a local R-hat to improve MCMC convergence diagnostic

Diagnosing convergence of Markov chain Monte Carlo is crucial and remain...

Asymptotic bias of inexact Markov Chain Monte Carlo methods in high dimension

This paper establishes non-asymptotic bounds on Wasserstein distances be...

Convergence of diffusions and their discretizations: from continuous to discrete processes and back

In this paper, we establish new quantitative convergence bounds for a cl...

The (1+1)-ES Reliably Overcomes Saddle Points

It is known that step size adaptive evolution strategies (ES) do not con...

Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics

We study the convergence in total variation and V-norm of discretization...