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 . This method relies on a regularisation procedure involving the Moreau-Yosida envelope of the indicator function associated with . Explicit convergence bounds in total variation norm and in Wasserstein distance of order 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.
Cite
@article{arxiv.1705.08964,
title = {Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo},
author = {Nicolas Brosse and Alain Durmus and Éric Moulines and Marcelo Pereyra},
journal= {arXiv preprint arXiv:1705.08964},
year = {2017}
}