Volume 4, Issue 3
Stability for Constrained Minimax Optimization

Yu-Hong Dai & Liwei Zhang

CSIAM Trans. Appl. Math., 4 (2023), pp. 542-565.

Published online: 2023-04

Export citation
  • Abstract

Minimax optimization problems are an important class of optimization problems arising from both modern machine learning and from traditional research areas. We focus on the stability of constrained minimax optimization problems based on the notion of local minimax point by Dai and Zhang (2020). Firstly, we extend the classical Jacobian uniqueness conditions of nonlinear programming to the constrained minimax problem and prove that this set of properties is stable with respect to small $\mathcal{C}^2$ perturbation. Secondly, we provide a set of conditions, called Property A, which does not require the strict complementarity condition for the upper level constraints. Finally, we prove that Property A is a sufficient condition for the strong regularity of the Kurash-Kuhn-Tucker (KKT) system at the KKT point, and it is also a sufficient condition for the local Lipschitzian homeomorphism of the Kojima mapping near the KKT point.

  • AMS Subject Headings

90C30

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{CSIAM-AM-4-542, author = {Dai , Yu-Hong and Zhang , Liwei}, title = {Stability for Constrained Minimax Optimization}, journal = {CSIAM Transactions on Applied Mathematics}, year = {2023}, volume = {4}, number = {3}, pages = {542--565}, abstract = {

Minimax optimization problems are an important class of optimization problems arising from both modern machine learning and from traditional research areas. We focus on the stability of constrained minimax optimization problems based on the notion of local minimax point by Dai and Zhang (2020). Firstly, we extend the classical Jacobian uniqueness conditions of nonlinear programming to the constrained minimax problem and prove that this set of properties is stable with respect to small $\mathcal{C}^2$ perturbation. Secondly, we provide a set of conditions, called Property A, which does not require the strict complementarity condition for the upper level constraints. Finally, we prove that Property A is a sufficient condition for the strong regularity of the Kurash-Kuhn-Tucker (KKT) system at the KKT point, and it is also a sufficient condition for the local Lipschitzian homeomorphism of the Kojima mapping near the KKT point.

}, issn = {2708-0579}, doi = {https://doi.org/10.4208/csiam-am.SO-2021-0040}, url = {http://global-sci.org/intro/article_detail/csiam-am/21641.html} }
TY - JOUR T1 - Stability for Constrained Minimax Optimization AU - Dai , Yu-Hong AU - Zhang , Liwei JO - CSIAM Transactions on Applied Mathematics VL - 3 SP - 542 EP - 565 PY - 2023 DA - 2023/04 SN - 4 DO - http://doi.org/10.4208/csiam-am.SO-2021-0040 UR - https://global-sci.org/intro/article_detail/csiam-am/21641.html KW - Constrained minimax optimization, Jacobian uniqueness conditions, strong regularity, strong sufficient optimality condition, Kojima mapping, local Lipschitzian homeomorphism. AB -

Minimax optimization problems are an important class of optimization problems arising from both modern machine learning and from traditional research areas. We focus on the stability of constrained minimax optimization problems based on the notion of local minimax point by Dai and Zhang (2020). Firstly, we extend the classical Jacobian uniqueness conditions of nonlinear programming to the constrained minimax problem and prove that this set of properties is stable with respect to small $\mathcal{C}^2$ perturbation. Secondly, we provide a set of conditions, called Property A, which does not require the strict complementarity condition for the upper level constraints. Finally, we prove that Property A is a sufficient condition for the strong regularity of the Kurash-Kuhn-Tucker (KKT) system at the KKT point, and it is also a sufficient condition for the local Lipschitzian homeomorphism of the Kojima mapping near the KKT point.

Dai , Yu-Hong and Zhang , Liwei. (2023). Stability for Constrained Minimax Optimization. CSIAM Transactions on Applied Mathematics. 4 (3). 542-565. doi:10.4208/csiam-am.SO-2021-0040
Copy to clipboard
The citation has been copied to your clipboard