Asynchronous stochastic convex optimization over random networks

Error bounds

B. Touri, Angelia Nedich, S. Sundhar Ram

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

7 Citations (Scopus)

Abstract

We consider a distributed multi-agent network system where the goal is to minimize the sum of convex functions, each of which is known (with stochastic errors) to a specific network agent. We are interested in asynchronous algorithms for solving the problem over a connected network where the communications among the agent are random. At each time, a random set of agents communicate and update their information. When updating, an agent uses the (sub)gradient of its individual objective function and its own stepsize value. The algorithm is completely asynchronous as it neither requires the coordination of agent actions nor the coordination of the stepsize values. We investigate the asymptotic error bounds of the algorithm with a constant stepsize for strongly convex and just convex functions. Our error bounds capture the effects of agent stepsize choices and the structure of the agent connectivity graph. The error bound scales at best as m in the number m of agents when the agent objective functions are strongly convex.

Original languageEnglish (US)
Title of host publication2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings
Pages342-351
Number of pages10
DOIs
StatePublished - 2010
Externally publishedYes
Event2010 Information Theory and Applications Workshop, ITA 2010 - San Diego, CA, United States
Duration: Jan 31 2010Feb 5 2010

Other

Other2010 Information Theory and Applications Workshop, ITA 2010
CountryUnited States
CitySan Diego, CA
Period1/31/102/5/10

Fingerprint

Convex optimization
Communication

Keywords

  • Algorithms
  • Asynchronous algorithms
  • Convex optimization
  • Networked system
  • Random consensus
  • Stochastic

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Touri, B., Nedich, A., & Ram, S. S. (2010). Asynchronous stochastic convex optimization over random networks: Error bounds. In 2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings (pp. 342-351). [5454103] https://doi.org/10.1109/ITA.2010.5454103

Asynchronous stochastic convex optimization over random networks : Error bounds. / Touri, B.; Nedich, Angelia; Ram, S. Sundhar.

2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings. 2010. p. 342-351 5454103.

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

Touri, B, Nedich, A & Ram, SS 2010, Asynchronous stochastic convex optimization over random networks: Error bounds. in 2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings., 5454103, pp. 342-351, 2010 Information Theory and Applications Workshop, ITA 2010, San Diego, CA, United States, 1/31/10. https://doi.org/10.1109/ITA.2010.5454103
Touri B, Nedich A, Ram SS. Asynchronous stochastic convex optimization over random networks: Error bounds. In 2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings. 2010. p. 342-351. 5454103 https://doi.org/10.1109/ITA.2010.5454103
Touri, B. ; Nedich, Angelia ; Ram, S. Sundhar. / Asynchronous stochastic convex optimization over random networks : Error bounds. 2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings. 2010. pp. 342-351
@inproceedings{dbe30a270a854f4cb387a2ffa02a1f6c,
title = "Asynchronous stochastic convex optimization over random networks: Error bounds",
abstract = "We consider a distributed multi-agent network system where the goal is to minimize the sum of convex functions, each of which is known (with stochastic errors) to a specific network agent. We are interested in asynchronous algorithms for solving the problem over a connected network where the communications among the agent are random. At each time, a random set of agents communicate and update their information. When updating, an agent uses the (sub)gradient of its individual objective function and its own stepsize value. The algorithm is completely asynchronous as it neither requires the coordination of agent actions nor the coordination of the stepsize values. We investigate the asymptotic error bounds of the algorithm with a constant stepsize for strongly convex and just convex functions. Our error bounds capture the effects of agent stepsize choices and the structure of the agent connectivity graph. The error bound scales at best as m in the number m of agents when the agent objective functions are strongly convex.",
keywords = "Algorithms, Asynchronous algorithms, Convex optimization, Networked system, Random consensus, Stochastic",
author = "B. Touri and Angelia Nedich and Ram, {S. Sundhar}",
year = "2010",
doi = "10.1109/ITA.2010.5454103",
language = "English (US)",
isbn = "9781424470143",
pages = "342--351",
booktitle = "2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings",

}

TY - GEN

T1 - Asynchronous stochastic convex optimization over random networks

T2 - Error bounds

AU - Touri, B.

AU - Nedich, Angelia

AU - Ram, S. Sundhar

PY - 2010

Y1 - 2010

N2 - We consider a distributed multi-agent network system where the goal is to minimize the sum of convex functions, each of which is known (with stochastic errors) to a specific network agent. We are interested in asynchronous algorithms for solving the problem over a connected network where the communications among the agent are random. At each time, a random set of agents communicate and update their information. When updating, an agent uses the (sub)gradient of its individual objective function and its own stepsize value. The algorithm is completely asynchronous as it neither requires the coordination of agent actions nor the coordination of the stepsize values. We investigate the asymptotic error bounds of the algorithm with a constant stepsize for strongly convex and just convex functions. Our error bounds capture the effects of agent stepsize choices and the structure of the agent connectivity graph. The error bound scales at best as m in the number m of agents when the agent objective functions are strongly convex.

AB - We consider a distributed multi-agent network system where the goal is to minimize the sum of convex functions, each of which is known (with stochastic errors) to a specific network agent. We are interested in asynchronous algorithms for solving the problem over a connected network where the communications among the agent are random. At each time, a random set of agents communicate and update their information. When updating, an agent uses the (sub)gradient of its individual objective function and its own stepsize value. The algorithm is completely asynchronous as it neither requires the coordination of agent actions nor the coordination of the stepsize values. We investigate the asymptotic error bounds of the algorithm with a constant stepsize for strongly convex and just convex functions. Our error bounds capture the effects of agent stepsize choices and the structure of the agent connectivity graph. The error bound scales at best as m in the number m of agents when the agent objective functions are strongly convex.

KW - Algorithms

KW - Asynchronous algorithms

KW - Convex optimization

KW - Networked system

KW - Random consensus

KW - Stochastic

UR - http://www.scopus.com/inward/record.url?scp=77952691286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952691286&partnerID=8YFLogxK

U2 - 10.1109/ITA.2010.5454103

DO - 10.1109/ITA.2010.5454103

M3 - Conference contribution

SN - 9781424470143

SP - 342

EP - 351

BT - 2010 Information Theory and Applications Workshop, ITA 2010 - Conference Proceedings

ER -