Title :
On the rate of convergence of distributed subgradient methods for multi-agent optimization
Author :
Nedic, Angelia ; Ozdaglar, Asuman
Author_Institution :
Univ. of Illinois Urbana-Champaign, Urbana
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 :
control system analysis; control system synthesis; convergence; decentralised control; multi-robot systems; convergence rate; distributed subgradient methods; multi-agent optimization; Algorithm design and analysis; Computational modeling; Computer industry; Convergence; Distributed computing; Electrical equipment industry; Industrial control; Optimization methods; Resource management; USA Councils;
Conference_Titel :
Decision and Control, 2007 46th IEEE Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
978-1-4244-1497-0
Electronic_ISBN :
0191-2216
DOI :
10.1109/CDC.2007.4434693
