Passer à la navigation principale Passer à la recherche Passer au contenu principal

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

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

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

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.

langue originaleAnglais
titre53rd IEEE Conference on Decision and Control,CDC 2014
EditeurInstitute of Electrical and Electronics Engineers Inc.
Pages5046-5051
Nombre de pages6
EditionFebruary
ISBN (Electronique)9781479977468
Les DOIs
étatPublié - 1 janv. 2014
Evénement2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014 - Los Angeles, États-Unis
Durée: 15 déc. 201417 déc. 2014

Série de publications

NomProceedings of the IEEE Conference on Decision and Control
nombreFebruary
Volume2015-February
ISSN (imprimé)0743-1546
ISSN (Electronique)2576-2370

Une conférence

Une conférence2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014
Pays/TerritoireÉtats-Unis
La villeLos Angeles
période15/12/1417/12/14

Empreinte digitale

Examiner les sujets de recherche de « Linear convergence rate for distributed optimization with the alternating direction method of multipliers ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation