Computer Science – Information Theory
Scientific paper
2011-04-14
Computer Science
Information Theory
7 pages
Scientific paper
In this paper, we analyze the convergence of a distributed Robbins-Monro algorithm for both constrained and unconstrained optimization in multi-agent systems. The algorithm searches for local minima of a (nonconvex) objective function which is supposed to coincide with a sum of local utility functions of the agents. The algorithm under study consists of two steps: a local stochastic gradient descent at each agent and a gossip step that drives the network of agents to a consensus. It is proved that i) an agreement is achieved between agents on the value of the estimate, ii) the algorithm converges to the set of Kuhn-Tucker points of the optimization problem. The proof relies on recent results about differential inclusions. In the context of unconstrained optimization, intelligible sufficient conditions are provided in order to ensure the stability of the algorithm. In the latter case, we also provide a central limit theorem which governs the asymptotic fluctuations of the estimate. We illustrate our results in the case of distributed power allocation for ad-hoc wireless networks.
Bianchi Pascal
Jakubowicz Jérémie
No associations
LandOfFree
Distributed Stochastic Approximation for Constrained and Unconstrained Optimization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Distributed Stochastic Approximation for Constrained and Unconstrained Optimization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Distributed Stochastic Approximation for Constrained and Unconstrained Optimization will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-166807