Show simple item record

dc.contributor.authorSalim, Adil
dc.contributor.authorKovalev, Dmitry
dc.contributor.authorRichtarik, Peter
dc.date.accessioned2019-11-27T11:51:05Z
dc.date.available2019-11-27T11:51:05Z
dc.date.issued2019-05-28
dc.identifier.urihttp://hdl.handle.net/10754/660280
dc.description.abstractWe 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.
dc.description.sponsorshipThe first author is grateful to Sholom Schechtman for his help in the numerical experiments.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/1905.11768
dc.rightsArchived with thanks to arXiv
dc.titleStochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
dc.typePreprint
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentKing Abdullah University of Science and Technology, Thuwal, Saudi Arabia
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.eprint.versionPre-print
dc.identifier.arxivid1905.11768
kaust.personSalim, Adil
kaust.personKovalev, Dmitry
kaust.personRichtarik, Peter
refterms.dateFOA2019-11-27T11:51:22Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
673.9Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record