Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo

Abstract

This paper presents a detailed theoretical analysis of the Langevin Monte Carlo sampling algorithm recently introduced in Durmus et al. (Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau, 2016) when applied to log-concave probability distributions that are restricted to a convex body $\mathsf{K}$. This method relies on a regularisation procedure involving the Moreau-Yosida envelope of the indicator function associated with $\mathsf{K}$. Explicit convergence bounds in total variation norm and in Wasserstein distance of order $1$ are established. In particular, we show that the complexity of this algorithm given a first order oracle is polynomial in the dimension of the state space. Finally, some numerical experiments are presented to compare our method with competing MCMC approaches from the literature.

References in corpus (1)

• Sampling constrained probability distributions using Spherical Augmentation

Cited by in corpus (8)

• Proximal nested sampling for high-dimensional Bayesian model selection
• On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
• An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
• Simplest random walk for approximating Robin boundary value problems and ergodic limits of reflected diffusions
• Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm
• Accelerating proximal Markov chain Monte Carlo by using an explicit stabilised method
• Sensing Cox Processes via Posterior Sampling and Positive Bases
• Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learning