dc.contributor.author Salim, Adil dc.contributor.author Sun, Lukang dc.contributor.author Richtarik, Peter dc.date.accessioned 2021-06-09T06:22:41Z dc.date.available 2021-06-09T06:22:41Z dc.date.issued 2021-06-06 dc.identifier.uri http://hdl.handle.net/10754/669465 dc.description.abstract We 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.publisher arXiv dc.relation.url https://arxiv.org/pdf/2106.03076.pdf dc.rights Archived with thanks to arXiv dc.title Complexity Analysis of Stein Variational Gradient Descent Under Talagrand's Inequality T1 dc.type Preprint dc.contributor.department Computer Science Program dc.contributor.department Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division dc.contributor.department Visual Computing Center (VCC) dc.eprint.version Pre-print dc.identifier.arxivid 2106.03076 kaust.person Salim, Adil kaust.person Sun, Lukang kaust.person Richtarik, Peter refterms.dateFOA 2021-06-09T06:23:04Z
﻿

Files in this item

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