Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Proceedings of Machine Learning Research Year : 2017

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 [DMP16] when applied to log-concave probability distributions that are restricted to a convex body K. This method relies on a regularisation procedure involving the Moreau-Yosida envelope of the indicator function associated with 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.
Fichier principal
Vignette du fichier
main.pdf (516.76 Ko) Télécharger le fichier
Loading...

Dates and versions

hal-01648665 , version 1 (27-11-2017)

Identifiers

  • HAL Id : hal-01648665 , version 1

Cite

Nicolas Brosse, Alain Durmus, Éric Moulines, Marcelo Pereyra. Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo. Proceedings of Machine Learning Research, 2017, 65, pp.319-342. ⟨hal-01648665⟩
241 View
103 Download

Share

Gmail Facebook X LinkedIn More