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

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...

Full description

Saved in:
Bibliographic Details
Published in:Chinese Control and Decision Conference pp. 4261 - 4266
Main Authors: Hou, Jie, Zeng, Xianlin
Format: Conference Proceeding
Language:English
Published: IEEE 15.08.2022
Subjects:
Convergence
Convergence Rate
Distributed Algorithm
Distributed computing
Optimization
Projection-Free Method
Saddle-Point Problem
ISSN:1948-9447
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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/k 2 ) 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.
ISSN:1948-9447
DOI:10.1109/CCDC55256.2022.10033870