Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning

Myung Cho, Lifeng Lai, Weiyu Xu

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

Abstract

With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distributed dual coordinate ascent in a star network to a general tree structured network, and provide the convergence rate analysis of the general distributed dual coordinate ascent. In numerical experiments, we demonstrate that the performance of the distributed dual coordinate ascent in a tree network can outperform that of the distributed dual coordinate ascent in a star network when a network has a lot of communication delays between the center node and its direct child nodes.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3512-3516
Number of pages5
ISBN (Electronic)9781479981311
DOIs
StatePublished - May 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: May 12 2019May 17 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period5/12/195/17/19

Fingerprint

Stars
Learning systems
Telecommunication networks
Explosions
Communication
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Cho, M., Lai, L., & Xu, W. (2019). Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 3512-3516). [8682185] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682185
Cho, Myung ; Lai, Lifeng ; Xu, Weiyu. / Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3512-3516 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{4605f05412204aeca7313db71996fe56,
title = "Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning",
abstract = "With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distributed dual coordinate ascent in a star network to a general tree structured network, and provide the convergence rate analysis of the general distributed dual coordinate ascent. In numerical experiments, we demonstrate that the performance of the distributed dual coordinate ascent in a tree network can outperform that of the distributed dual coordinate ascent in a star network when a network has a lot of communication delays between the center node and its direct child nodes.",
author = "Myung Cho and Lifeng Lai and Weiyu Xu",
year = "2019",
month = "5",
doi = "10.1109/ICASSP.2019.8682185",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3512--3516",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
address = "United States",

}

Cho, M, Lai, L & Xu, W 2019, Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8682185, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 3512-3516, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 5/12/19. https://doi.org/10.1109/ICASSP.2019.8682185

Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning. / Cho, Myung; Lai, Lifeng; Xu, Weiyu.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3512-3516 8682185 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

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

TY - GEN

T1 - Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning

AU - Cho, Myung

AU - Lai, Lifeng

AU - Xu, Weiyu

PY - 2019/5

Y1 - 2019/5

N2 - With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distributed dual coordinate ascent in a star network to a general tree structured network, and provide the convergence rate analysis of the general distributed dual coordinate ascent. In numerical experiments, we demonstrate that the performance of the distributed dual coordinate ascent in a tree network can outperform that of the distributed dual coordinate ascent in a star network when a network has a lot of communication delays between the center node and its direct child nodes.

AB - With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distributed dual coordinate ascent in a star network to a general tree structured network, and provide the convergence rate analysis of the general distributed dual coordinate ascent. In numerical experiments, we demonstrate that the performance of the distributed dual coordinate ascent in a tree network can outperform that of the distributed dual coordinate ascent in a star network when a network has a lot of communication delays between the center node and its direct child nodes.

UR - http://www.scopus.com/inward/record.url?scp=85068981658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068981658&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682185

DO - 10.1109/ICASSP.2019.8682185

M3 - Conference contribution

AN - SCOPUS:85068981658

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

SP - 3512

EP - 3516

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Cho M, Lai L, Xu W. Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3512-3516. 8682185. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8682185