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

Pascal Bianchi; Gersende Fort; Walid Hachem; Jérémie Jakubowicz

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

Pascal Bianchi
, Gersende Fort
, Walid Hachem
, Jérémie Jakubowicz

Centre national de la recherche scientifique

Research output: Contribution to journal › Conference article › peer-review

Abstract

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.

Original language	English
Pages (from-to)	1030-1034
Number of pages	5
Journal	European Signal Processing Conference
Publication status	Published - 1 Dec 2011
Event	19th European Signal Processing Conference, EUSIPCO 2011 - Barcelona, Spain Duration: 29 Aug 2011 → 2 Sept 2011

Cite this

@article{104f6be0d2c34fe0b7af7fb58a0d83f3,

title = "Performance analysis of a distributed Robbins-Monro algorithm for sensor networks",

abstract = "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.",

author = "Pascal Bianchi and Gersende Fort and Walid Hachem and J{\'e}r{\'e}mie Jakubowicz",

year = "2011",

month = dec,

day = "1",

language = "English",

pages = "1030--1034",

journal = "European Signal Processing Conference",

issn = "2219-5491",

note = "19th European Signal Processing Conference, EUSIPCO 2011 ; Conference date: 29-08-2011 Through 02-09-2011",

}

TY - JOUR

T1 - Performance analysis of a distributed Robbins-Monro algorithm for sensor networks

AU - Bianchi, Pascal

AU - Fort, Gersende

AU - Hachem, Walid

AU - Jakubowicz, Jérémie

PY - 2011/12/1

Y1 - 2011/12/1

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/84863756321

M3 - Conference article

AN - SCOPUS:84863756321

SN - 2219-5491

SP - 1030

EP - 1034

JO - European Signal Processing Conference

JF - European Signal Processing Conference

T2 - 19th European Signal Processing Conference, EUSIPCO 2011

Y2 - 29 August 2011 through 2 September 2011

ER -

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

Abstract

Other files and links

Fingerprint

Cite this