Distributed Stochastic Approximation: Weak Convergence and Network Design
Applications
2016-09-05 v2 Optimization and Control
Abstract
This paper studies distributed stochastic approximation algorithms based on broadcast gossip on communication networks represented by digraphs. Weak convergence of these algorithms is proved, and an associated ordinary differential equation (ODE) is formulated connecting convergence points with local objective functions and network properties. Using these results, a methodology is proposed for network design, aimed at achieving the desired asymptotic behavior at consensus. Convergence rate of the algorithm is also analyzed and further improved using an attached stochastic differential equation. Simulation results illustrate the theoretical concepts.
Keywords
Cite
@article{arxiv.1412.3158,
title = {Distributed Stochastic Approximation: Weak Convergence and Network Design},
author = {Miloš S. Stanković and Nemanja Ilić and Srdjan S. Stanković},
journal= {arXiv preprint arXiv:1412.3158},
year = {2016}
}