CaltechAUTHORS
  A Caltech Library Service

Logarithmic Communication for Distributed Optimization in Multi-Agent Systems

London, Palma and Vardi, Shai and Wierman, Adam (2020) Logarithmic Communication for Distributed Optimization in Multi-Agent Systems. ACM SIGMETRICS Performance Evaluation Review, 48 (1). pp. 97-98. ISSN 0163-5999. https://resolver.caltech.edu/CaltechAUTHORS:20200709-141943501

[img] PDF - Published Version
See Usage Policy.

1013Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200709-141943501

Abstract

Classically, the design of multi-agent systems is approached using techniques from distributed optimization such as dual descent and consensus algorithms. Such algorithms depend on convergence to global consensus before any individual agent can determine its local action. This leads to challenges with respect to communication overhead and robustness, and improving algorithms with respect to these measures has been a focus of the community for decades. This paper presents a new approach for multi-agent system design based on ideas from the emerging field of local computation algorithms. The framework we develop, LOcal Convex Optimization (LOCO), is the first local computation algorithm for convex optimization problems and can be applied in a wide-variety of settings. We demonstrate the generality of the framework via applications to Network Utility Maximization (NUM) and the distributed training of Support Vector Machines (SVMs), providing numerical results illustrating the improvement compared to classical distributed optimization approaches in each case.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1145/3393691.3394197DOIArticle
https://resolver.caltech.edu/CaltechAUTHORS:20191218-160307829Related ItemConference Paper
Additional Information:© 2020 Copyright held by the owner/author(s). This work was supported in part by NSF grants AitF-1637598, CNS-1518941, CPS-154471, the Linde Institute, and an Amazon Fellowship in Artificial Intelligence.
Funders:
Funding AgencyGrant Number
NSFAitF-1637598
NSFCNS-1518941
NSFCPS-154471
Linde Institute of Economic and Management ScienceUNSPECIFIED
AmazonUNSPECIFIED
Subject Keywords:distributed algorithms; distributed optimization; multi-agent systems
Issue or Number:1
Record Number:CaltechAUTHORS:20200709-141943501
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200709-141943501
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:104314
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:09 Jul 2020 21:42
Last Modified:04 Nov 2020 19:44

Repository Staff Only: item control page