CoChat
Sign Up
Cited by 10Distributed Control Multi-Agent SystemsOptimization and Variational AnalysisAdvanced Optimization Algorithms Research

The DOI matches its Crossref record.

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

Iutzeler, F., Bianchi, P., Ciblat, Ph., Hachem, W.·2014·53rd IEEE Conference on Decision and Control
DOI 10.1109/cdc.2014.7040177
Open this paper in CoChat — free account

Abstract

Consider the problem of distributed optimization where a network of N agents cooperate to solve a minimization problem of the form infxequation where function fnis 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 fnare 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.

Overview

Integrity signals

Registry

Crossref · 10.1109/cdc.2014.7040177

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 25

  1. monteiro, 2010, Iteration-complexity of block-decomposition algorithms and the Alternating Direction Method of Multipliers, Optimization Online Preprint, 2713, 1
  2. 10.1137/110836936 · DOI
  3. 10.1109/CDC.2012.6425904 · DOI
  4. 10.1109/GlobalSIP.2013.6736937 · DOI · Paper page
  5. goldfarb, 2012, Fast alternating linearization methods for minimizing the sum of two convex functions, Mathematical Programming, 1
  6. deng, 2012, On the global and linear convergence of the generalized Alternating Direction Method of Multipliers, Tech Rep Rice University
  7. 10.1137/120878951 · DOI
  8. jakovetic, 2013, Linear Convergence Rate of a Class of Distributed Augmented Lagrangian Algorithms, ArXiv e-prints
  9. shi, 2013, On the Linear Convergence of the ADMM in Decentralized Consensus Optimization, ArXiv e-prints
  10. 10.1109/TAC.2014.2354892 · DOI
  11. 10.1109/TAC.2012.2209984 · DOI
  12. 10.1109/JPROC.2006.887322 · DOI
  13. 10.1109/TIT.2013.2275131 · DOI
  14. 10.1109/TAC.2009.2037460 · DOI
  15. 10.1561/2200000016 · DOI · Paper page
  16. combettes, 2011, Proximal splitting methods in signal processing, Fixed-Point Algorithms for Inverse Problems in Sci Eng, 185, 10.1007/978-1-4419-9569-8_10 · DOI
  17. agarwal, 2011, A reliable effective terascale linear learning system, Ar Xiv e-prints
  18. 10.1109/TSP.2007.906734 · DOI
  19. 10.1145/1791212.1791218 · DOI
  20. hong, 2013, On the Linear Convergence of the Alternating Direction Method of Multipliers, ArXiv e-prints
  21. 10.1007/BF01581204 · DOI
  22. bauschke, 2011, Convex analysis and monotone operator theory in Hilbert spaces CMS Books in Mathemat-ics/Ouvrages de Mathematiques de la SMC
  23. 10.1137/0716071 · DOI
  24. iutzelcr, 2013, Asynchronous distributed optimization using a randomized Alternating Direction Method of Multipliers, Proc IEEE Conf Decision Contr (CDC)
  25. iutzelcr, 2014, Explicit convergence rate of a distributed alternating direction method of multipliers, Submitted available on arXiv

Cited by

Sorted by citations

Metadata

Authors
Iutzeler, F., Bianchi, P., Ciblat, P., & Hachem, W.
Affiliations
  • Supélec (FR)
  • Centre National de la Recherche Scientifique (FR)
ORCID
Venue
53rd IEEE Conference on Decision and Control
Publisher
IEEE
Published
2014-12
Pages
5046-5051
ISSN
0191-2216 (ISSN-L)
DOI
10.1109/cdc.2014.7040177
OpenAlex
W2089969453
Cited by
10
References
0
Citations by year
2025: 1 · 2019: 1 · 2018: 2 · 2017: 3 · 2015: 3
FWCI
1.56
Type
conference paper
Language
en
Open access
closed
Locations
  • IEEE Conference on Decision and Control (CDC) (publishedVersion)
  • HAL (submittedVersion)
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
  • Physical Sciences › Mathematics › Numerical Analysis › Advanced Optimization Algorithms Research
Keywords
distributed optimization, alternating direction method of multipliers, linear convergence, convergence rate, consensus, convex optimization, multi-agent systems, hyperparameter optimization, twice differentiable functions

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review