Transport map unadjusted Langevin algorithms: learning and discretizing perturbed samplers
From MaRDI portal
Publication:6426458
arXiv2302.07227MaRDI QIDQ6426458FDOQ6426458
Authors: Benjamin J. Zhang, Youssef M. Marzouk, Konstantinos Spiliopoulos 
Publication date: 14 February 2023
Abstract: Langevin dynamics are widely used in sampling high-dimensional, non-Gaussian distributions whose densities are known up to a normalizing constant. In particular, there is strong interest in unadjusted Langevin algorithms (ULA), which directly discretize Langevin dynamics to estimate expectations over the target distribution. We study the use of transport maps that approximately normalize a target distribution as a way to precondition and accelerate the convergence of Langevin dynamics. We show that in continuous time, when a transport map is applied to Langevin dynamics, the result is a Riemannian manifold Langevin dynamics (RMLD) with metric defined by the transport map. This connection suggests more systematic ways of learning metrics, and also yields alternative discretizations of the RMLD described by the map, which we study. Moreover, we show that under certain conditions, when the transport map is used in conjunction with ULA, we can improve the geometric rate of convergence of the output process in the 2--Wasserstein distance. Illustrative numerical results complement our theoretical claims.
Statistical sampling theory and related topics (62D99) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)
This page was built for publication: Transport map unadjusted Langevin algorithms: learning and discretizing perturbed samplers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6426458)
