On the rate of convergence of distributed subgradient methods for multi-agent optimization

Angelia Nedich, Asuman Ozdaglar

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

51 Citations (Scopus)

Abstract

We study a distributed computation model for optimizing the sum of convex (nonsmooth) objective functions of multiple agents. We provide convergence results and estimates for convergence rate. Our analysis explicitly characterizes the tradeoff between the accuracy of the approximate optimal solutions generated and the number of iterations needed to achieve the given accuracy.

Original languageEnglish (US)
Title of host publicationProceedings of the 46th IEEE Conference on Decision and Control 2007, CDC
Pages4711-4716
Number of pages6
DOIs
StatePublished - 2007
Externally publishedYes
Event46th IEEE Conference on Decision and Control 2007, CDC - New Orleans, LA, United States
Duration: Dec 12 2007Dec 14 2007

Other

Other46th IEEE Conference on Decision and Control 2007, CDC
CountryUnited States
CityNew Orleans, LA
Period12/12/0712/14/07

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality
  • Chemical Health and Safety

Cite this

Nedich, A., & Ozdaglar, A. (2007). On the rate of convergence of distributed subgradient methods for multi-agent optimization. In Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC (pp. 4711-4716). [4434693] https://doi.org/10.1109/CDC.2007.4434693

On the rate of convergence of distributed subgradient methods for multi-agent optimization. / Nedich, Angelia; Ozdaglar, Asuman.

Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC. 2007. p. 4711-4716 4434693.

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

Nedich, A & Ozdaglar, A 2007, On the rate of convergence of distributed subgradient methods for multi-agent optimization. in Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC., 4434693, pp. 4711-4716, 46th IEEE Conference on Decision and Control 2007, CDC, New Orleans, LA, United States, 12/12/07. https://doi.org/10.1109/CDC.2007.4434693
Nedich A, Ozdaglar A. On the rate of convergence of distributed subgradient methods for multi-agent optimization. In Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC. 2007. p. 4711-4716. 4434693 https://doi.org/10.1109/CDC.2007.4434693
Nedich, Angelia ; Ozdaglar, Asuman. / On the rate of convergence of distributed subgradient methods for multi-agent optimization. Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC. 2007. pp. 4711-4716
@inproceedings{652cd4f821854eb19d2bafd4e26761b9,
title = "On the rate of convergence of distributed subgradient methods for multi-agent optimization",
abstract = "We study a distributed computation model for optimizing the sum of convex (nonsmooth) objective functions of multiple agents. We provide convergence results and estimates for convergence rate. Our analysis explicitly characterizes the tradeoff between the accuracy of the approximate optimal solutions generated and the number of iterations needed to achieve the given accuracy.",
author = "Angelia Nedich and Asuman Ozdaglar",
year = "2007",
doi = "10.1109/CDC.2007.4434693",
language = "English (US)",
isbn = "1424414989",
pages = "4711--4716",
booktitle = "Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC",

}

TY - GEN

T1 - On the rate of convergence of distributed subgradient methods for multi-agent optimization

AU - Nedich, Angelia

AU - Ozdaglar, Asuman

PY - 2007

Y1 - 2007

N2 - We study a distributed computation model for optimizing the sum of convex (nonsmooth) objective functions of multiple agents. We provide convergence results and estimates for convergence rate. Our analysis explicitly characterizes the tradeoff between the accuracy of the approximate optimal solutions generated and the number of iterations needed to achieve the given accuracy.

AB - We study a distributed computation model for optimizing the sum of convex (nonsmooth) objective functions of multiple agents. We provide convergence results and estimates for convergence rate. Our analysis explicitly characterizes the tradeoff between the accuracy of the approximate optimal solutions generated and the number of iterations needed to achieve the given accuracy.

UR - http://www.scopus.com/inward/record.url?scp=62749193789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62749193789&partnerID=8YFLogxK

U2 - 10.1109/CDC.2007.4434693

DO - 10.1109/CDC.2007.4434693

M3 - Conference contribution

AN - SCOPUS:62749193789

SN - 1424414989

SN - 9781424414987

SP - 4711

EP - 4716

BT - Proceedings of the 46th IEEE Conference on Decision and Control 2007, CDC

ER -