Stochastic Fista Algorithms: So Fast?

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Motivated by challenges in Computational Statistics such as Penalized Maximum Likelihood inference in statistical models with intractable likelihoods, we analyze the convergence of a stochastic perturbation of the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA), when the stochastic approximation relies on a biased Monte Carlo estimation as it happens when the points are drawn from a Markov chain Monte Carlo (MCMC) sampler. We first motivate this general framework and then show a convergence result for the perturbed FISTA algorithm. We discuss the convergence rate of this algorithm and the computational cost of the Monte Carlo approximation to reach a given precision. Finally, through a numerical example, we explore new directions for a better understanding of these Proximal-Gradient based stochastic optimization algorithms.

Original languageEnglish
Title of host publication2018 IEEE Statistical Signal Processing Workshop, SSP 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages388-392
Number of pages5
ISBN (Print)9781538615706
DOIs
Publication statusPublished - 29 Aug 2018
Event20th IEEE Statistical Signal Processing Workshop, SSP 2018 - Freiburg im Breisgau, Germany
Duration: 10 Jun 201813 Jun 2018

Publication series

Name2018 IEEE Statistical Signal Processing Workshop, SSP 2018

Conference

Conference20th IEEE Statistical Signal Processing Workshop, SSP 2018
Country/TerritoryGermany
CityFreiburg im Breisgau
Period10/06/1813/06/18

Keywords

  • Computational Statistics
  • Markov chain Monte Carlo
  • Nesterov acceleration
  • Proximal-Gradient algorithms
  • Stochastic Approximation

Fingerprint

Dive into the research topics of 'Stochastic Fista Algorithms: So Fast?'. Together they form a unique fingerprint.

Cite this