PERFORMANCE ANALYSIS OF A DISTRIBUTED ROBBINS-MONRO ALGORITHM FOR SENSOR NETWORKS

被引：0

作者：

Bianchi, Pascal ^{[1
]}

Fort, Gersende ^{[1
]}

Hachem, Walid ^{[1
]}

Jakabowicz, Jeremie ^{[1
]}

机构：

[1] TELECOM ParisTech, CNRS, LTC, 46 Rue Barrault, F-75634 Paris 13, France

来源：

19TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO-2011) | 2011年

关键词：

STOCHASTIC-APPROXIMATION; CONVERGENCE;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper investigates the rate of convergence of a distributed Robbins-Morro algorithm for sensor networks. The algorithm under study consists of two steps: a local Robbins-Morro 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.

引用

页码：1030 / 1034

页数：5

共 15 条

[1] Decentralized maximum-likelihood estimation for sensor networks composed of nonlinearly coupled dynamical systems
Barbarossa, Sergio
Scutari, Gesualdo
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2007, 55 (07) : 3456 - 3470
[2] Bertsekas D.P., 1989, PARALLEL DISTRIBUTED
[3] Bianchi P., 2011, ICASSP
[4] Randomized gossip algorithms
Boyd, Stephen
Ghosh, Arpita
Prabhakar, Balaji
Shah, Devavrat
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (06) : 2508 - 2530
[5] Delyon B, 1999, ANN STAT, V27, P94
[6] Gadat S, 2007, J MACH LEARN RES, V8, P509
[7] Kelly FP, 1998, J OPER RES SOC, V49, P237, DOI 10.1057/palgrave.jors.2600523
[8] Kushner H. J., 2003, Stochastic Approximation and Recursive Algorithms and Applications, volume35 of Applications of Mathematics (New York). Stochastic Modelling and Applied Probability, V2nd
[9] Pelletier M, 1998, ANN APPL PROBAB, V8, P10
[10] Rabbat M, 2004, IPSN '04: THIRD INTERNATIONAL SYMPOSIUM ON INFORMATION PROCESSING IN SENSOR NETWORKS, P20

← 1 2 →