Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem

Jie Hou; Xianlin Zeng

doi:10.1109/CCDC55256.2022.10033870

Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem

Jie Hou, Xianlin Zeng^*

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

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

2 Citations (Scopus)

Abstract

We consider a two-network saddle-point problem with constraints, whose projections are expensive. We propose a projection-free algorithm, which is referred to as Distributed Frank-Wolfe Saddle-Point algorithm (DFWSP), which combines the gradient tracking technique and Frank-Wolfe technique. We prove that the algorithm achieves O(1/k2) convergence rate for strongly-convex-strongly-concave saddle-point problems. We empirically shows that the proposed algorithm has better numerical performance than the distributed projected saddle-point algorithm.

Original language	English
Title of host publication	Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4261-4266
Number of pages	6
ISBN (Electronic)	9781665478960
DOIs	https://doi.org/10.1109/CCDC55256.2022.10033870
Publication status	Published - 2022
Event	34th Chinese Control and Decision Conference, CCDC 2022 - Hefei, China Duration: 15 Aug 2022 → 17 Aug 2022

Publication series

Name	Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

Conference

Conference	34th Chinese Control and Decision Conference, CCDC 2022
Country/Territory	China
City	Hefei
Period	15/08/22 → 17/08/22

Keywords

Convergence Rate
Distributed Algorithm
Projection-Free Method
Saddle-Point Problem

Access to Document

10.1109/CCDC55256.2022.10033870

Cite this

Hou, J., & Zeng, X. (2022). Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem. In Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022 (pp. 4261-4266). (Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCDC55256.2022.10033870

@inproceedings{6b84efcb97a0437eae7dd091aa12174c,

title = "Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem",

abstract = "We consider a two-network saddle-point problem with constraints, whose projections are expensive. We propose a projection-free algorithm, which is referred to as Distributed Frank-Wolfe Saddle-Point algorithm (DFWSP), which combines the gradient tracking technique and Frank-Wolfe technique. We prove that the algorithm achieves O(1/k2) convergence rate for strongly-convex-strongly-concave saddle-point problems. We empirically shows that the proposed algorithm has better numerical performance than the distributed projected saddle-point algorithm.",

keywords = "Convergence Rate, Distributed Algorithm, Projection-Free Method, Saddle-Point Problem",

author = "Jie Hou and Xianlin Zeng",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 34th Chinese Control and Decision Conference, CCDC 2022 ; Conference date: 15-08-2022 Through 17-08-2022",

year = "2022",

doi = "10.1109/CCDC55256.2022.10033870",

language = "English",

series = "Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4261--4266",

booktitle = "Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022",

address = "United States",

}

Hou, J & Zeng, X 2022, Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem. in Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022. Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 4261-4266, 34th Chinese Control and Decision Conference, CCDC 2022, Hefei, China, 15/08/22. https://doi.org/10.1109/CCDC55256.2022.10033870

Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem. / Hou, Jie; Zeng, Xianlin.
Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 4261-4266 (Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022).

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

TY - GEN

T1 - Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem

AU - Hou, Jie

AU - Zeng, Xianlin

PY - 2022

Y1 - 2022

N2 - We consider a two-network saddle-point problem with constraints, whose projections are expensive. We propose a projection-free algorithm, which is referred to as Distributed Frank-Wolfe Saddle-Point algorithm (DFWSP), which combines the gradient tracking technique and Frank-Wolfe technique. We prove that the algorithm achieves O(1/k2) convergence rate for strongly-convex-strongly-concave saddle-point problems. We empirically shows that the proposed algorithm has better numerical performance than the distributed projected saddle-point algorithm.

AB - We consider a two-network saddle-point problem with constraints, whose projections are expensive. We propose a projection-free algorithm, which is referred to as Distributed Frank-Wolfe Saddle-Point algorithm (DFWSP), which combines the gradient tracking technique and Frank-Wolfe technique. We prove that the algorithm achieves O(1/k2) convergence rate for strongly-convex-strongly-concave saddle-point problems. We empirically shows that the proposed algorithm has better numerical performance than the distributed projected saddle-point algorithm.

KW - Convergence Rate

KW - Distributed Algorithm

KW - Projection-Free Method

KW - Saddle-Point Problem

UR - http://www.scopus.com/inward/record.url?scp=85149577887&partnerID=8YFLogxK

U2 - 10.1109/CCDC55256.2022.10033870

DO - 10.1109/CCDC55256.2022.10033870

M3 - Conference contribution

AN - SCOPUS:85149577887

T3 - Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

SP - 4261

EP - 4266

BT - Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 34th Chinese Control and Decision Conference, CCDC 2022

Y2 - 15 August 2022 through 17 August 2022

ER -

Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this