On the rate of convergence of distributed subgradient methods for multi-agent optimization
- 1 January 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4711-4716
- https://doi.org/10.1109/cdc.2007.4434693
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.Keywords
This publication has 11 references indexed in Scilit:
- Convergence in Multiagent Coordination, Consensus, and FlockingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Quantized ConsensusPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Gossip algorithms: design, analysis and applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The Mathematics of Internet Congestion ControlPublished by Springer Science and Business Media LLC ,2004
- Coordination of groups of mobile autonomous agents using nearest neighbor rulesIEEE Transactions on Automatic Control, 2003
- Incremental Subgradient Methods for Nondifferentiable OptimizationSIAM Journal on Optimization, 2001
- Rate control for communication networks: shadow prices, proportional fairness and stabilityJournal of the Operational Research Society, 1998
- Novel Type of Phase Transition in a System of Self-Driven ParticlesPhysical Review Letters, 1995
- Distributed asynchronous deterministic and stochastic gradient optimization algorithmsIEEE Transactions on Automatic Control, 1986
- Products of Indecomposable, Aperiodic, Stochastic MatricesProceedings of the American Mathematical Society, 1963