Distributed mini-batch random projection algorithms for reduced communication overhead

Soomin Lee; Angelia Nedic

doi:10.1109/GlobalSIP.2013.6736939

Distributed mini-batch random projection algorithms for reduced communication overhead

Soomin Lee, Angelia Nedic

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

1 Scopus citations

Abstract

We propose a gossip-based mini-batch random projection (GMRP) algorithm that can reduce communication overhead for a distributed optimization problem defined over a network with a very large number of constraints. We state a convergence result and provide an application of the GMRP, text classification with support vector machines.

Original language	English (US)
Title of host publication	2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings
Pages	559-562
Number of pages	4
DOIs	https://doi.org/10.1109/GlobalSIP.2013.6736939
State	Published - Dec 1 2013
Externally published	Yes
Event	2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Austin, TX, United States Duration: Dec 3 2013 → Dec 5 2013

Publication series

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

Other

Other	2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013
Country/Territory	United States
City	Austin, TX
Period	12/3/13 → 12/5/13

ASJC Scopus subject areas

Information Systems
Signal Processing

Access to Document

10.1109/GlobalSIP.2013.6736939

Cite this

Lee, S., & Nedic, A. (2013). Distributed mini-batch random projection algorithms for reduced communication overhead. In 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings (pp. 559-562). Article 6736939 (2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings). https://doi.org/10.1109/GlobalSIP.2013.6736939

Distributed mini-batch random projection algorithms for reduced communication overhead. / Lee, Soomin; Nedic, Angelia.
2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings. 2013. p. 559-562 6736939 (2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings).

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

Lee, S & Nedic, A 2013, Distributed mini-batch random projection algorithms for reduced communication overhead. in 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings., 6736939, 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings, pp. 559-562, 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.2013.6736939

@inproceedings{2c533a25df494143a5ff93d7ad83e91f,

title = "Distributed mini-batch random projection algorithms for reduced communication overhead",

abstract = "We propose a gossip-based mini-batch random projection (GMRP) algorithm that can reduce communication overhead for a distributed optimization problem defined over a network with a very large number of constraints. We state a convergence result and provide an application of the GMRP, text classification with support vector machines.",

author = "Soomin Lee and Angelia Nedic",

year = "2013",

month = dec,

day = "1",

doi = "10.1109/GlobalSIP.2013.6736939",

language = "English (US)",

isbn = "9781479902484",

series = "2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings",

pages = "559--562",

booktitle = "2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings",

note = "2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 ; Conference date: 03-12-2013 Through 05-12-2013",

}

TY - GEN

T1 - Distributed mini-batch random projection algorithms for reduced communication overhead

AU - Lee, Soomin

AU - Nedic, Angelia

PY - 2013/12/1

Y1 - 2013/12/1

N2 - We propose a gossip-based mini-batch random projection (GMRP) algorithm that can reduce communication overhead for a distributed optimization problem defined over a network with a very large number of constraints. We state a convergence result and provide an application of the GMRP, text classification with support vector machines.

AB - We propose a gossip-based mini-batch random projection (GMRP) algorithm that can reduce communication overhead for a distributed optimization problem defined over a network with a very large number of constraints. We state a convergence result and provide an application of the GMRP, text classification with support vector machines.

UR - http://www.scopus.com/inward/record.url?scp=84897691817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897691817&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2013.6736939

DO - 10.1109/GlobalSIP.2013.6736939

M3 - Conference contribution

AN - SCOPUS:84897691817

SN - 9781479902484

T3 - 2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings

SP - 559

EP - 562

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

T2 - 2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013

Y2 - 3 December 2013 through 5 December 2013

ER -

Distributed mini-batch random projection algorithms for reduced communication overhead

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this