Distributed subgradient projection algorithm for convex optimization

S. Sundhar Ram; A. Nedić; V. V. Veeravalli

doi:10.1109/ICASSP.2009.4960418

Distributed subgradient projection algorithm for convex optimization

S. Sundhar Ram, A. Nedić, V. V. Veeravalli

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

33 Scopus citations

Abstract

We consider constrained minimization of a sum of convex functions over a convex and compact set, when each component function is known only to a specific agent in a timevarying peer to peer network. We study an iterative optimization algorithm in which each agent obtains a weighted average of its own iterate with the iterates of its neighbors, updates the average using the subgradient of its local function and then projects onto the constraint set to generate the new iterate. We obtain error bounds on the limit of the function value when a constant stepsize is used.

Original language	English (US)
Title of host publication	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009
Pages	3653-3656
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2009.4960418
State	Published - 2009
Externally published	Yes
Event	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China Duration: Apr 19 2009 → Apr 24 2009

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Other

Other	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
Country/Territory	Taiwan, Province of China
City	Taipei
Period	4/19/09 → 4/24/09

Keywords

Distributed optimization
Subgradient algorithm
Time-varying network

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2009.4960418

Cite this

Sundhar Ram, S., Nedić, A., & Veeravalli, V. V. (2009). Distributed subgradient projection algorithm for convex optimization. In 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009 (pp. 3653-3656). Article 4960418 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2009.4960418

Distributed subgradient projection algorithm for convex optimization. / Sundhar Ram, S.; Nedić, A.; Veeravalli, V. V.
2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009. 2009. p. 3653-3656 4960418 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

Sundhar Ram, S, Nedić, A & Veeravalli, VV 2009, Distributed subgradient projection algorithm for convex optimization. in 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009., 4960418, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 3653-3656, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, Taiwan, Province of China, 4/19/09. https://doi.org/10.1109/ICASSP.2009.4960418

Sundhar Ram S, Nedić A, Veeravalli VV. Distributed subgradient projection algorithm for convex optimization. In 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009. 2009. p. 3653-3656. 4960418. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2009.4960418

@inproceedings{8fa0f742e076429f823f52af700f60d6,

title = "Distributed subgradient projection algorithm for convex optimization",

abstract = "We consider constrained minimization of a sum of convex functions over a convex and compact set, when each component function is known only to a specific agent in a timevarying peer to peer network. We study an iterative optimization algorithm in which each agent obtains a weighted average of its own iterate with the iterates of its neighbors, updates the average using the subgradient of its local function and then projects onto the constraint set to generate the new iterate. We obtain error bounds on the limit of the function value when a constant stepsize is used.",

keywords = "Distributed optimization, Subgradient algorithm, Time-varying network",

author = "{Sundhar Ram}, S. and A. Nedi{\'c} and Veeravalli, {V. V.}",

year = "2009",

doi = "10.1109/ICASSP.2009.4960418",

language = "English (US)",

isbn = "9781424423545",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "3653--3656",

booktitle = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009",

note = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 ; Conference date: 19-04-2009 Through 24-04-2009",

}

TY - GEN

T1 - Distributed subgradient projection algorithm for convex optimization

AU - Sundhar Ram, S.

AU - Nedić, A.

AU - Veeravalli, V. V.

PY - 2009

Y1 - 2009

N2 - We consider constrained minimization of a sum of convex functions over a convex and compact set, when each component function is known only to a specific agent in a timevarying peer to peer network. We study an iterative optimization algorithm in which each agent obtains a weighted average of its own iterate with the iterates of its neighbors, updates the average using the subgradient of its local function and then projects onto the constraint set to generate the new iterate. We obtain error bounds on the limit of the function value when a constant stepsize is used.

AB - We consider constrained minimization of a sum of convex functions over a convex and compact set, when each component function is known only to a specific agent in a timevarying peer to peer network. We study an iterative optimization algorithm in which each agent obtains a weighted average of its own iterate with the iterates of its neighbors, updates the average using the subgradient of its local function and then projects onto the constraint set to generate the new iterate. We obtain error bounds on the limit of the function value when a constant stepsize is used.

KW - Distributed optimization

KW - Subgradient algorithm

KW - Time-varying network

UR - http://www.scopus.com/inward/record.url?scp=70349194622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349194622&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2009.4960418

DO - 10.1109/ICASSP.2009.4960418

M3 - Conference contribution

AN - SCOPUS:70349194622

SN - 9781424423545

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 3653

EP - 3656

BT - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009

T2 - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009

Y2 - 19 April 2009 through 24 April 2009

ER -

Distributed subgradient projection algorithm for convex optimization

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this