Mathematics – Optimization and Control
Scientific paper
2012-03-07
Mathematics
Optimization and Control
27 pages
Scientific paper
In this paper, a distributed stochastic approximation algorithm is studied. Applications of such algorithms include decentralized estimation, optimization, control or computing. The algorithm consists in two steps: a local step, where each node in a network updates a local estimate using a stochastic approximation algorithm with decreasing step size, and a gossip step, where a node computes a local weighted average between its estimates and those of its neighbors. Convergence of the estimates toward a consensus is established under weak assumptions. The approach relies on two main ingredients: the existence of a Lyapunov function for the mean field in the agreement subspace, and a contraction property of the random matrices of weights in the subspace orthogonal to the agreement subspace. A second order analysis of the algorithm is also performed under the form of a Central Limit Theorem. The Polyak-averaged version of the algorithm is also considered.
Bianchi Pascal
Fort Gersende
Hachem Walid
No associations
LandOfFree
Performance of a Distributed Stochastic Approximation Algorithm 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 Performance of a Distributed Stochastic Approximation Algorithm, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Performance of a Distributed Stochastic Approximation Algorithm will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-394363