Skip to main navigation Skip to search Skip to main content

Linear convergence rate for distributed optimization with the alternating direction method of multipliers

  • Écl. Sup. d'Élec.
  • Telecom Paris

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

Abstract

Consider the problem of distributed optimization where a network of N agents cooperate to solve a minimization problem of the form infx equation where function fn is convex and known only by agent n. The Alternating Direction Method of Multipliers (ADMM) has shown to be particularly efficient to solve this kind of problem. In this paper, we assume that there exists a unique minimum x and that the functions fn are twice differentiable at x and verify equation where the inequality is taken in the positive definite ordering. Under these assumptions, we prove the linear convergence of the distributed ADMM to the consensus over x and derive a tight convergence rate. Finally, we give examples where one can derive the ADMM hyper-parameter ρ corresponding to the optimal rate.

Original languageEnglish
Title of host publication53rd IEEE Conference on Decision and Control,CDC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5046-5051
Number of pages6
EditionFebruary
ISBN (Electronic)9781479977468
DOIs
Publication statusPublished - 1 Jan 2014
Event2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014 - Los Angeles, United States
Duration: 15 Dec 201417 Dec 2014

Publication series

NameProceedings of the IEEE Conference on Decision and Control
NumberFebruary
Volume2015-February
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370

Conference

Conference2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014
Country/TerritoryUnited States
CityLos Angeles
Period15/12/1417/12/14

Keywords

  • Alternating Direction Method of Multipliers
  • Consensus algorithms
  • Distributed optimization

Fingerprint

Dive into the research topics of 'Linear convergence rate for distributed optimization with the alternating direction method of multipliers'. Together they form a unique fingerprint.

Cite this