Asynchronous distributed principal component analysis using stochastic approximation

Gemma Morral; Pascal Bianchi; Jeremie Jakubowicz

doi:10.1109/CDC.2012.6425898

Asynchronous distributed principal component analysis using stochastic approximation

Gemma Morral
, Pascal Bianchi
, Jeremie Jakubowicz

CNRS

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

Résumé

In this paper we address the problem of asynchronous distributed principal component analysis. We provide several algorithms coping with different situations according to the underlying graph structure. A general enough framework allows us to analyze all these algorithms at the same time. Convergence is proved with probability 1 under suitable assumptions, and numerical experiments illustrate their good behavior.

langue originale	Anglais
Numéro d'article	6425898
Pages (de - à)	1398-1403
Nombre de pages	6
journal	Proceedings of the IEEE Conference on Decision and Control
Les DOIs	https://doi.org/10.1109/CDC.2012.6425898
état	Publié - 1 janv. 2012
Evénement	51st IEEE Conference on Decision and Control, CDC 2012 - Maui, HI, États-Unis Durée: 10 déc. 2012 → 13 déc. 2012

Accès au document

10.1109/CDC.2012.6425898

Autres fichiers et liens

Lien vers la publication dans Scopus

Contient cette citation

@article{8e3ef0d45e74472fbaba043f6a6485dd,

title = "Asynchronous distributed principal component analysis using stochastic approximation",

abstract = "In this paper we address the problem of asynchronous distributed principal component analysis. We provide several algorithms coping with different situations according to the underlying graph structure. A general enough framework allows us to analyze all these algorithms at the same time. Convergence is proved with probability 1 under suitable assumptions, and numerical experiments illustrate their good behavior.",

keywords = "Asynchronous algorithm, Distributed algorithm, Oja's algorithm, Principal Component Analysis, Stochastic Approximation, Wireless Sensor Network",

author = "Gemma Morral and Pascal Bianchi and Jeremie Jakubowicz",

year = "2012",

month = jan,

day = "1",

doi = "10.1109/CDC.2012.6425898",

language = "English",

pages = "1398--1403",

journal = "Proceedings of the IEEE Conference on Decision and Control",

issn = "0743-1546",

note = "51st IEEE Conference on Decision and Control, CDC 2012 ; Conference date: 10-12-2012 Through 13-12-2012",

}

TY - JOUR

T1 - Asynchronous distributed principal component analysis using stochastic approximation

AU - Morral, Gemma

AU - Bianchi, Pascal

AU - Jakubowicz, Jeremie

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In this paper we address the problem of asynchronous distributed principal component analysis. We provide several algorithms coping with different situations according to the underlying graph structure. A general enough framework allows us to analyze all these algorithms at the same time. Convergence is proved with probability 1 under suitable assumptions, and numerical experiments illustrate their good behavior.

AB - In this paper we address the problem of asynchronous distributed principal component analysis. We provide several algorithms coping with different situations according to the underlying graph structure. A general enough framework allows us to analyze all these algorithms at the same time. Convergence is proved with probability 1 under suitable assumptions, and numerical experiments illustrate their good behavior.

KW - Asynchronous algorithm

KW - Distributed algorithm

KW - Oja's algorithm

KW - Principal Component Analysis

KW - Stochastic Approximation

KW - Wireless Sensor Network

UR - https://www.scopus.com/pages/publications/84874245224

U2 - 10.1109/CDC.2012.6425898

DO - 10.1109/CDC.2012.6425898

M3 - Conference article

AN - SCOPUS:84874245224

SN - 0743-1546

SP - 1398

EP - 1403

JO - Proceedings of the IEEE Conference on Decision and Control

JF - Proceedings of the IEEE Conference on Decision and Control

M1 - 6425898

T2 - 51st IEEE Conference on Decision and Control, CDC 2012

Y2 - 10 December 2012 through 13 December 2012

ER -

Asynchronous distributed principal component analysis using stochastic approximation

Résumé

Accès au document

Autres fichiers et liens

Empreinte digitale

Contient cette citation