On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case

Ngoc Huy Chau, Éric Moulines, Miklos Rásonyi, Sotirios Sabanis, Ying Zhang

Research output: Contribution to journalArticlepeer-review

Abstract

We consider the problem of sampling from a target distribution which is \emph{not necessarily logconcave}. Non-asymptotic analysis results are established in a suitable Wasserstein-type distance of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm, when the gradient is driven by even \emph{dependent} data streams. Our estimates are sharper and \emph{uniform} in the number of iterations, in contrast to those in previous studies.
Original languageEnglish
Number of pages33
JournalSIAM Journal on the Mathematics of Data Science (SIMODS)
Publication statusAccepted/In press - 19 Jun 2021

Keywords

  • math.ST
  • math.PR
  • stat.ML
  • stat.TH
  • 65C40, 62L10

Fingerprint

Dive into the research topics of 'On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case'. Together they form a unique fingerprint.

Cite this