Higher Order Langevin Monte Carlo Algorithm
Abstract
A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented. All these are obtained in the context of sampling from a target distribution that has a density on known up to a normalizing constant. Moreover, is assumed to have a locally Lipschitz gradient and its third derivative is locally H\"{o}lder continuous with exponent . Non-asymptotic bounds are obtained for the convergence to stationarity of the new sampling method with convergence rate in Wasserstein distance, while it is shown that the rate is 1 in total variation even in the absence of convexity. Finally, in the case where is strongly convex and its gradient is Lipschitz continuous, explicit constants are provided.
Cite
@article{arxiv.1808.00728,
title = {Higher Order Langevin Monte Carlo Algorithm},
author = {Sotirios Sabanis and Ying Zhang},
journal= {arXiv preprint arXiv:1808.00728},
year = {2019}
}
Comments
47 pages