Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
From MaRDI portal
Publication:6319495
arXiv1905.11768MaRDI QIDQ6319495
Peter Richtárik, Adil Salim, Dmitry Kovalev
Publication date: 28 May 2019
Abstract: We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of one stochastic smooth term and multiple stochastic nonsmooth terms. In each iteration, our splitting technique only requires access to a stochastic gradient of the smooth term and a stochastic proximal operator for each of the nonsmooth terms. We establish nonasymptotic sublinear and linear convergence rates under convexity and strong convexity of the smooth term, respectively, expressed in terms of the KL divergence and Wasserstein distance. We illustrate the efficiency of our sampling technique through numerical simulations on a Bayesian learning task.
Has companion code repository: https://github.com/adil-salim/SPLA
This page was built for publication: Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6319495)
