TY - GEN
T1 - Accelerated Primal-dual Scheme for a Class of Stochastic Nonconvex-concave Saddle Point Problems
AU - Boroun, Morteza
AU - Alizadeh, Zeinab
AU - Jalilzadeh, Afrooz
N1 - Publisher Copyright: © 2023 American Automatic Control Council.
PY - 2023
Y1 - 2023
N2 - Stochastic nonconvex-concave min-max saddle point problems appear in many machine learning and control problems including distributionally robust optimization, generative adversarial networks, and adversarial learning. In this paper, we consider a class of nonconvex saddle point problems where the objective function satisfies the Polyak-Łojasiewicz condition with respect to the minimization variable and it is concave with respect to the maximization variable. The existing methods for solving nonconvex-concave saddle point problems often suffer from slow convergence and/or contain multiple loops. Our main contribution lies in proposing a novel single-loop accelerated primal-dual algorithm with new convergence rate results appearing for the first time in the literature, to the best of our knowledge.
AB - Stochastic nonconvex-concave min-max saddle point problems appear in many machine learning and control problems including distributionally robust optimization, generative adversarial networks, and adversarial learning. In this paper, we consider a class of nonconvex saddle point problems where the objective function satisfies the Polyak-Łojasiewicz condition with respect to the minimization variable and it is concave with respect to the maximization variable. The existing methods for solving nonconvex-concave saddle point problems often suffer from slow convergence and/or contain multiple loops. Our main contribution lies in proposing a novel single-loop accelerated primal-dual algorithm with new convergence rate results appearing for the first time in the literature, to the best of our knowledge.
UR - http://www.scopus.com/inward/record.url?scp=85167794603&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85167794603&partnerID=8YFLogxK
U2 - 10.23919/ACC55779.2023.10156371
DO - 10.23919/ACC55779.2023.10156371
M3 - Conference contribution
T3 - Proceedings of the American Control Conference
SP - 204
EP - 209
BT - 2023 American Control Conference, ACC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 American Control Conference, ACC 2023
Y2 - 31 May 2023 through 2 June 2023
ER -