Show simple item record

dc.contributor.authorSalim, Adil
dc.contributor.authorSun, Lukang
dc.contributor.authorRichtarik, Peter
dc.date.accessioned2021-06-09T06:22:41Z
dc.date.available2021-06-09T06:22:41Z
dc.date.issued2021-06-06
dc.identifier.urihttp://hdl.handle.net/10754/669465
dc.description.abstractWe study the complexity of Stein Variational Gradient Descent (SVGD), which is an algorithm to sample from $\pi(x) \propto \exp(-F(x))$ where $F$ smooth and nonconvex. We provide a clean complexity bound for SVGD in the population limit in terms of the Stein Fisher Information (or squared Kernelized Stein Discrepancy), as a function of the dimension of the problem $d$ and the desired accuracy $\varepsilon$. Unlike existing work, we do not make any assumption on the trajectory of the algorithm. Instead, our key assumption is that the target distribution satisfies Talagrand's inequality T1.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2106.03076.pdf
dc.rightsArchived with thanks to arXiv
dc.titleComplexity Analysis of Stein Variational Gradient Descent Under Talagrand's Inequality T1
dc.typePreprint
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.contributor.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.identifier.arxivid2106.03076
kaust.personSalim, Adil
kaust.personSun, Lukang
kaust.personRichtarik, Peter
refterms.dateFOA2021-06-09T06:23:04Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
216.6Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record