Abstract : We analyze the convergence of the distributed multi-agent optimization scheme originally proposed in [1]. In this scheme, a number of agents cooperate to estimate the minimum of the sum of their locally-known cost functions. We consider a special case for which the collective cost function is strongly convex and where the agent communication graph is fixed. Whereas the analysis in [1] focuses on the suboptimality of the Ces'aro averages of the agents' sequences, we establish explicit ultimate bounds on the agents' estimation errors themselves. We demonstrate that the collective optimum is globally practically asymptotically stable for this algorithm.
Type de document :
Communication dans un congrès
Roberto Cominetti and Sylvain Sorin and Bruno Tuffin. NetGCOOP 2011 : International conference on NETwork Games, COntrol and OPtimization, Oct 2011, Paris, France. IEEE, 2011
https://hal.inria.fr/hal-00644455
Contributeur : Ist Rennes
<>
Soumis le : jeudi 24 novembre 2011 - 14:40:50
Dernière modification le : lundi 20 juin 2016 - 14:10:32
Document(s) archivé(s) le : lundi 5 décembre 2016 - 10:57:54
Karla Kvaternik, Lacra Pavel. Lyapunov Analysis of a Distributed Optimization Scheme. Roberto Cominetti and Sylvain Sorin and Bruno Tuffin. NetGCOOP 2011 : International conference on NETwork Games, COntrol and OPtimization, Oct 2011, Paris, France. IEEE, 2011. 〈hal-00644455〉
