Distributed Gaussian learning over time-varying directed graphs

Angelia Nedich; Alex Olshevsky; Cesar A. Uribe

doi:10.1109/ACSSC.2016.7869674

Distributed Gaussian learning over time-varying directed graphs

Angelia Nedich, Alex Olshevsky, Cesar A. Uribe

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of O(1/k) with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.

Original language	English (US)
Title of host publication	Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	1710-1714
Number of pages	5
ISBN (Electronic)	9781538639542
DOIs	https://doi.org/10.1109/ACSSC.2016.7869674
State	Published - Mar 1 2017
Event	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States Duration: Nov 6 2016 → Nov 9 2016

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)	1058-6393

Other

Other	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Country/Territory	United States
City	Pacific Grove
Period	11/6/16 → 11/9/16

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/ACSSC.2016.7869674

Cite this

Nedich, A., Olshevsky, A., & Uribe, C. A. (2017). Distributed Gaussian learning over time-varying directed graphs. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 1710-1714). [7869674] (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869674

Distributed Gaussian learning over time-varying directed graphs. / Nedich, Angelia; Olshevsky, Alex; Uribe, Cesar A.

Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. ed. / Michael B. Matthews. IEEE Computer Society, 2017. p. 1710-1714 7869674 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nedich, A, Olshevsky, A & Uribe, CA 2017, Distributed Gaussian learning over time-varying directed graphs. in MB Matthews (ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869674, Conference Record - Asilomar Conference on Signals, Systems and Computers, IEEE Computer Society, pp. 1710-1714, 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, United States, 11/6/16. https://doi.org/10.1109/ACSSC.2016.7869674

Nedich A, Olshevsky A, Uribe CA. Distributed Gaussian learning over time-varying directed graphs. In Matthews MB, editor, Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 1710-1714. 7869674. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2016.7869674

@inproceedings{9247f0b8384c44fdb1b5845e8a18211c,

title = "Distributed Gaussian learning over time-varying directed graphs",

abstract = "We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of O(1/k) with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.",

author = "Angelia Nedich and Alex Olshevsky and Uribe, {Cesar A.}",

note = "Funding Information: This research is supported partially by the National Science Foundation under grants no. CNS 15-44953 and no. CMMI-1463262, and by the Office of Naval Research under grant no. N00014-12-1-0998 Publisher Copyright: {\textcopyright} 2016 IEEE.; 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 ; Conference date: 06-11-2016 Through 09-11-2016",

year = "2017",

month = mar,

day = "1",

doi = "10.1109/ACSSC.2016.7869674",

language = "English (US)",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "1710--1714",

editor = "Matthews, {Michael B.}",

booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",

}

TY - GEN

T1 - Distributed Gaussian learning over time-varying directed graphs

AU - Nedich, Angelia

AU - Olshevsky, Alex

AU - Uribe, Cesar A.

N1 - Funding Information: This research is supported partially by the National Science Foundation under grants no. CNS 15-44953 and no. CMMI-1463262, and by the Office of Naval Research under grant no. N00014-12-1-0998 Publisher Copyright: © 2016 IEEE.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of O(1/k) with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.

AB - We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of O(1/k) with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.

UR - http://www.scopus.com/inward/record.url?scp=85016269504&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016269504&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2016.7869674

DO - 10.1109/ACSSC.2016.7869674

M3 - Conference contribution

AN - SCOPUS:85016269504

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1710

EP - 1714

BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

Y2 - 6 November 2016 through 9 November 2016

ER -

Distributed Gaussian learning over time-varying directed graphs

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this