A stochastic coordinate descent primal-dual algorithm and applications

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

Abstract

First, we introduce a splitting algorithm to minimize a sum of three convex functions. The algorithm is of primal dual kind and is inspired by recent results of V͡ and Condat. Second, we provide a randomized version of the algorithm based on the idea of coordinate descent. Finally, we address two applications of our method: (i) for stochastic minibatch optimization; and (ii) for distributed optimization.

Original languageEnglish
Title of host publicationIEEE International Workshop on Machine Learning for Signal Processing, MLSP
EditorsMamadou Mboup, Tulay Adali, Eric Moreau, Jan Larsen
PublisherIEEE Computer Society
ISBN (Electronic)9781479936946
DOIs
Publication statusPublished - 14 Nov 2014
Event2014 24th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2014 - Reims, France
Duration: 21 Sept 201424 Sept 2014

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Conference

Conference2014 24th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2014
Country/TerritoryFrance
CityReims
Period21/09/1424/09/14

Keywords

  • Consensus algorithms
  • Coordinate Descent
  • Distributed Optimization
  • Large-scale Learning
  • Primal-Dual Algorithm

Fingerprint

Dive into the research topics of 'A stochastic coordinate descent primal-dual algorithm and applications'. Together they form a unique fingerprint.

Cite this