Distributed optimization of strongly convex functions on directed time-varying graphs

Angelia Nedich, Alex Olshevsky

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

We investigate the convergence rate of the recently proposed subgadient-push method for distributed separable optimization over time-varying directed graphs. The algorithm requires no knowledge of either the number of agents or the graph sequence to implement, nor the use of doubly stochastic weights. We show that the algorithm converges at a rate of O(ln t/t) for strongly convex functions. The proportionality constant in the rate estimate depends on some problem parameters, the initial values at the nodes, the speed of the network information diffusion, and the imbalances of influence among the nodes.

Original languageEnglish (US)
Title of host publication2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings
Pages329-332
Number of pages4
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Austin, TX, United States
Duration: Dec 3 2013Dec 5 2013

Other

Other2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013
CountryUnited States
CityAustin, TX
Period12/3/1312/5/13

Fingerprint

Directed graphs

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Nedich, A., & Olshevsky, A. (2013). Distributed optimization of strongly convex functions on directed time-varying graphs. In 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings (pp. 329-332). [6736882] https://doi.org/10.1109/GlobalSIP.2013.6736882

Distributed optimization of strongly convex functions on directed time-varying graphs. / Nedich, Angelia; Olshevsky, Alex.

2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings. 2013. p. 329-332 6736882.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nedich, A & Olshevsky, A 2013, Distributed optimization of strongly convex functions on directed time-varying graphs. in 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings., 6736882, pp. 329-332, 2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013, Austin, TX, United States, 12/3/13. https://doi.org/10.1109/GlobalSIP.2013.6736882
Nedich A, Olshevsky A. Distributed optimization of strongly convex functions on directed time-varying graphs. In 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings. 2013. p. 329-332. 6736882 https://doi.org/10.1109/GlobalSIP.2013.6736882
Nedich, Angelia ; Olshevsky, Alex. / Distributed optimization of strongly convex functions on directed time-varying graphs. 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings. 2013. pp. 329-332
@inproceedings{3be739cdec1447a5b02a174111b6c879,
title = "Distributed optimization of strongly convex functions on directed time-varying graphs",
abstract = "We investigate the convergence rate of the recently proposed subgadient-push method for distributed separable optimization over time-varying directed graphs. The algorithm requires no knowledge of either the number of agents or the graph sequence to implement, nor the use of doubly stochastic weights. We show that the algorithm converges at a rate of O(ln t/t) for strongly convex functions. The proportionality constant in the rate estimate depends on some problem parameters, the initial values at the nodes, the speed of the network information diffusion, and the imbalances of influence among the nodes.",
author = "Angelia Nedich and Alex Olshevsky",
year = "2013",
doi = "10.1109/GlobalSIP.2013.6736882",
language = "English (US)",
isbn = "9781479902484",
pages = "329--332",
booktitle = "2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings",

}

TY - GEN

T1 - Distributed optimization of strongly convex functions on directed time-varying graphs

AU - Nedich, Angelia

AU - Olshevsky, Alex

PY - 2013

Y1 - 2013

N2 - We investigate the convergence rate of the recently proposed subgadient-push method for distributed separable optimization over time-varying directed graphs. The algorithm requires no knowledge of either the number of agents or the graph sequence to implement, nor the use of doubly stochastic weights. We show that the algorithm converges at a rate of O(ln t/t) for strongly convex functions. The proportionality constant in the rate estimate depends on some problem parameters, the initial values at the nodes, the speed of the network information diffusion, and the imbalances of influence among the nodes.

AB - We investigate the convergence rate of the recently proposed subgadient-push method for distributed separable optimization over time-varying directed graphs. The algorithm requires no knowledge of either the number of agents or the graph sequence to implement, nor the use of doubly stochastic weights. We show that the algorithm converges at a rate of O(ln t/t) for strongly convex functions. The proportionality constant in the rate estimate depends on some problem parameters, the initial values at the nodes, the speed of the network information diffusion, and the imbalances of influence among the nodes.

UR - http://www.scopus.com/inward/record.url?scp=84897687535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897687535&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2013.6736882

DO - 10.1109/GlobalSIP.2013.6736882

M3 - Conference contribution

SN - 9781479902484

SP - 329

EP - 332

BT - 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings

ER -