The University of Southampton
University of Southampton Institutional Repository

Distributed multiagent learning with a broadcast adaptive subgradient method

Distributed multiagent learning with a broadcast adaptive subgradient method
Distributed multiagent learning with a broadcast adaptive subgradient method
Many applications in multiagent learning are essentially convex optimization problems in which agents have only limited communication and partial information about the function being minimized (examples of such applications include, among others, coordinated source localization, distributed adaptive filtering, control, and coordination). Given this observation, we propose a new non-hierarchical decentralized algorithm for the asymptotic minimization of possibly time-varying convex functions. In our method each agent has knowledge of a time-varying local cost function, and the objective is to minimize asymptotically a global cost function defined by the sum of the local functions. At each iteration of our algorithm, agents improve their estimates of a minimizer of the global function by applying a particular version of the adaptive projected subgradient method to their local functions. Then the agents exchange and mix their improved estimates using a probabilistic model based on recent results in weighted average consensus algorithms. The resulting algorithm is provably optimal and reproduces as particular cases many existing algorithms (such as consensus algorithms and recent methods based on the adaptive projected subgradient method). To illustrate one possible application, we show how our algorithm can be applied to coordinated acoustic source localization in sensor networks
decentralized convex optimization, distributed computing, consensus, acoustic source localization
1039-1046
International Foundation for Autonomous Agents and Multiagent Systems
Cavalcante, R. L. G.
7c2e5089-c076-4287-8ba1-26c98bf30a14
Rogers, A.
f9130bc6-da32-474e-9fab-6c6cb8077fdc
Jennings, N. R.
ab3d94cc-247c-4545-9d1e-65873d6cdb30
Yamada, I.
472a0cab-1376-424e-9f08-676470cafc23
Cavalcante, R. L. G.
7c2e5089-c076-4287-8ba1-26c98bf30a14
Rogers, A.
f9130bc6-da32-474e-9fab-6c6cb8077fdc
Jennings, N. R.
ab3d94cc-247c-4545-9d1e-65873d6cdb30
Yamada, I.
472a0cab-1376-424e-9f08-676470cafc23

Cavalcante, R. L. G., Rogers, A., Jennings, N. R. and Yamada, I. (2010) Distributed multiagent learning with a broadcast adaptive subgradient method. In Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems. pp. 1039-1046 .

Record type: Conference or Workshop Item (Paper)

Abstract

Many applications in multiagent learning are essentially convex optimization problems in which agents have only limited communication and partial information about the function being minimized (examples of such applications include, among others, coordinated source localization, distributed adaptive filtering, control, and coordination). Given this observation, we propose a new non-hierarchical decentralized algorithm for the asymptotic minimization of possibly time-varying convex functions. In our method each agent has knowledge of a time-varying local cost function, and the objective is to minimize asymptotically a global cost function defined by the sum of the local functions. At each iteration of our algorithm, agents improve their estimates of a minimizer of the global function by applying a particular version of the adaptive projected subgradient method to their local functions. Then the agents exchange and mix their improved estimates using a probabilistic model based on recent results in weighted average consensus algorithms. The resulting algorithm is provably optimal and reproduces as particular cases many existing algorithms (such as consensus algorithms and recent methods based on the adaptive projected subgradient method). To illustrate one possible application, we show how our algorithm can be applied to coordinated acoustic source localization in sensor networks

Text
Cavalcante_AAMAS2010 - Accepted Manuscript
Download (263kB)
Text
Cavalcante_AAMAS2010.pdf - Version of Record
Download (263kB)
Other
eprint72297.txt - Other
Restricted to Repository staff only
Request a copy

More information

Submitted date: 13 October 2009
Published date: May 2010
Additional Information: Event Dates: May 10-14, 2010
Venue - Dates: Ninth International Conference on Autonomous Agents and Multiagent Systems, Toronto, Canada, 2010-05-10 - 2010-05-14
Keywords: decentralized convex optimization, distributed computing, consensus, acoustic source localization

Identifiers

Local EPrints ID: 72297
URI: http://eprints.soton.ac.uk/id/eprint/72297
PURE UUID: 2e6a0d77-b657-41b7-b9af-e3f59bc5c79f

Catalogue record

Date deposited: 08 Feb 2010
Last modified: 13 Mar 2024 21:24

Export record

Contributors

Author: R. L. G. Cavalcante
Author: A. Rogers
Author: N. R. Jennings
Author: I. Yamada

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×