TY - GEN
T1 - A Neurodynamic Approach for a Class of Convex-concave Minimax Problems
AU - Xie, Zehua
AU - Jiang, Xinrui
AU - Qin, Sitian
AU - Feng, Jiqiang
AU - Xu, Shengbing
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper presents a neurodynamic approach for a class of convex-concave minimax problems. First, variational inequalities are given, serving as the necessary and sufficient conditions for the desired saddle point of the underlying objective function. Next, based on the variational inequalities, a neurodynamic approach is designed for the minimax problems. Taking advantage of a proper Lyapunov function, the stability of the state solution of the proposed neurodynamic approach is guaranteed. Furthermore, the proposed neurodynamic approach is able to solve the non-quadratic convex-concave minimax problem exponentially. Compared with the existing researches for the quadratic minimax problem, the proposed neurodynamic approach has wider scope of applications to some extent. Finally, a numerical experiment is provided to show the effectiveness of the proposed neurodynamic approach.
AB - This paper presents a neurodynamic approach for a class of convex-concave minimax problems. First, variational inequalities are given, serving as the necessary and sufficient conditions for the desired saddle point of the underlying objective function. Next, based on the variational inequalities, a neurodynamic approach is designed for the minimax problems. Taking advantage of a proper Lyapunov function, the stability of the state solution of the proposed neurodynamic approach is guaranteed. Furthermore, the proposed neurodynamic approach is able to solve the non-quadratic convex-concave minimax problem exponentially. Compared with the existing researches for the quadratic minimax problem, the proposed neurodynamic approach has wider scope of applications to some extent. Finally, a numerical experiment is provided to show the effectiveness of the proposed neurodynamic approach.
KW - convex-concave minimax problem
KW - exponential convergence
KW - saddle point
UR - https://www.scopus.com/pages/publications/85142601797
U2 - 10.1109/ICIST55546.2022.9926965
DO - 10.1109/ICIST55546.2022.9926965
M3 - 会议稿件
AN - SCOPUS:85142601797
T3 - 2022 12th International Conference on Information Science and Technology, ICIST 2022
SP - 276
EP - 280
BT - 2022 12th International Conference on Information Science and Technology, ICIST 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th International Conference on Information Science and Technology, ICIST 2022
Y2 - 14 October 2022 through 16 October 2022
ER -