Performance analysis of a distributed Robbins-Monro algorithm for sensor networks

This paper investigates the rate of convergence of a distributed Robbins-Monro algorithm for sensor networks. The algorithm under study consists of two steps: a local Robbins-Monro step at each sensor and a gossip step that drives the network to a consensus. Under verifiable sufficient conditions, we give an explicit rate of convergence for this algorithm and provide a conditional Central Limit Theorem. Our results are applied to distributed source localization.

[1]  Alejandro Ribeiro,et al.  Consensus in Ad Hoc WSNs With Noisy Links—Part I: Distributed Estimation of Deterministic Signals , 2008, IEEE Transactions on Signal Processing.

[2]  Srdjan S. Stankovic,et al.  Decentralized Parameter Estimation by Consensus Based Stochastic Approximation , 2007, IEEE Transactions on Automatic Control.

[3]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[4]  Frank Kelly,et al.  Rate control for communication networks: shadow prices, proportional fairness and stability , 1998, J. Oper. Res. Soc..

[5]  Stephen P. Boyd,et al.  Randomized gossip algorithms , 2006, IEEE Transactions on Information Theory.

[6]  John N. Tsitsiklis,et al.  Parallel and distributed computation , 1989 .

[7]  Sergio Barbarossa,et al.  Decentralized Maximum-Likelihood Estimation for Sensor Networks Composed of Nonlinearly Coupled Dynamical Systems , 2006, IEEE Transactions on Signal Processing.

[8]  É. Moulines,et al.  Convergence of a stochastic approximation version of the EM algorithm , 1999 .

[9]  M. Pelletier.  Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing , 1998 .

[10]  Laurent Younes,et al.  A Stochastic Algorithm for Feature Selection in Pattern Recognition , 2007, J. Mach. Learn. Res..

[11]  Robert Nowak,et al.  Distributed optimization in sensor networks , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[12]  H. Kushner,et al.  Stochastic Approximation and Recursive Algorithms and Applications , 2003 .

[13]  B. Widrow,et al.  Stationary and nonstationary learning characteristics of the LMS adaptive filter , 1976, Proceedings of the IEEE.

[14]  Pascal Bianchi,et al.  Convergence of a distributed parameter estimator for sensor networks with local averaging of the estimates , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Angelia Nedic,et al.  Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization , 2008, J. Optim. Theory Appl..