Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
Statistics Theory
2016-12-20 v3 Computation
Methodology
Statistics Theory
Abstract
In this paper, we study a method to sample from a target distribution over having a positive density with respect to the Lebesgue measure, known up to a normalisation factor. This method is based on the Euler discretization of the overdamped Langevin stochastic differential equation associated with . For both constant and decreasing step sizes in the Euler discretization, we obtain non-asymptotic bounds for the convergence to the target distribution in total variation distance. A particular attention is paid to the dependency on the dimension , to demonstrate the applicability of this method in the high dimensional setting. These bounds improve and extend the results of (Dalalyan 2014).
Cite
@article{arxiv.1507.05021,
title = {Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm},
author = {Alain Durmus and Eric Moulines},
journal= {arXiv preprint arXiv:1507.05021},
year = {2016}
}