The Forward-Backward Envelope for Sampling with the Overdamped Langevin Algorithm

2022/01/22 by Eftekhari, Armin, Vargas, Luis, Zygalakis, Konstantinos · 2 citations
#FOS: Mathematics #Numerical Analysis (math.NA)

paper · doi:10.48550/arxiv.2201.09096

Abstract

In this paper, we analyse a proximal method based on the idea of forward-backward splitting for sampling from distributions with densities that are not necessarily smooth. In particular, we study the non-asymptotic properties of the Euler-Maruyama discretization of the Langevin equation, where the forward-backward envelope is used to deal with the non-smooth part of the dynamics. An advantage of this envelope, when compared to widely-used Moreu-Yoshida one and the MYULA algorithm, is that it maintains the MAP estimator of the original non-smooth distribution. We also study a number of numerical experiments that corroborate that support our theoretical findings.

Cited by

• Anchored Langevin Algorithms
• Piecewise Deterministic Sampling for Constrained Distributions

Related

• The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions
• The Tamed Unadjusted Langevin Algorithm
• Hadamard Langevin dynamics for sampling the l1-prior
• From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
• Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals