TY - GEN
T1 - Distributed Conditional Gradient Algorithm for Two-Network Saddle-point Problem
AU - Hou, Jie
AU - Zeng, Xianlin
N1 - Publisher Copyright:
© 2022 IEEE.
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 -