A consensus-based decentralized algorithm for non-convex optimization with application to dictionary learning

Hoi To Wai, Tsung Hui Chang, Anna Scaglione

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Scopus citations

Abstract

In handling massive-scale signal processing problems arising from 'big-data' applications, key technologies could come from the development of decentralized algorithms. In this context, consensus-based methods have been advocated because of their simplicity, fault tolerance and versatility. This paper presents a new consensus-based decentralized algorithm for a class of non-convex optimization problems that arises often in inference and learning problems, including 'sparse dictionary learning' as a special case. For the proposed algorithm, we provide sufficient conditions for convergence to a stationary point. Numerical results demonstrate the efficacy of the proposed algorithm and provide evidence that validates our convergence claim.

Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3546-3550
Number of pages5
ISBN (Electronic)9781467369978
DOIs
StatePublished - Aug 4 2015
Event40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia
Duration: Apr 19 2014Apr 24 2014

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2015-August
ISSN (Print)1520-6149

Other

Other40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Country/TerritoryAustralia
CityBrisbane
Period4/19/144/24/14

Keywords

  • decentralized algorithm
  • dictionary learning
  • non-convex optimization

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A consensus-based decentralized algorithm for non-convex optimization with application to dictionary learning'. Together they form a unique fingerprint.

Cite this