Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations

arXiv2104.12384MaRDI QIDQ6366106FDOQ6366106

Authors: Jesús María Sanz-Serna, Konstantinos C. Zygalakis 

Publication date: 26 April 2021

Abstract: We present a framework that allows for the non-asymptotic study of the $2$-Wasserstein distance between the invariant distribution of an ergodic stochastic differential equation and the distribution of its numerical approximation in the strongly log-concave case. This allows us to study in a unified way a number of different integrators proposed in the literature for the overdamped and underdamped Langevin dynamics. In addition, we analyse a novel splitting method for the underdamped Langevin dynamics which only requires one gradient evaluation per time step. Under an additional smoothness assumption on a $d$--dimensional strongly log-concave distribution with condition number $kappa$, the algorithm is shown to produce with an $$ complexity samples from a distribution that, in Wasserstein distance, is at most $epsilon>0$ away from the target distribution.

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

This page was built for publication: Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6366106)