Solutions of Two-stage Stochastic Minimax Problems
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908630952968192 |
|---|---|
| author | Sun, Hailin Chen, Xiaojun |
| author_facet | Sun, Hailin Chen, Xiaojun |
| contents | This paper introduces a class of two-stage stochastic minimax problems where the first-stage objective function is nonconvex-concave while the second-stage objective function is strongly convex-concave. We establish properties of the second-stage minimax value function and solution functions, and characterize the existence and relationships among saddle points, minimax points, and KKT points. We apply the sample average approximation (SAA) to the class of two-stage stochastic minimax problems and prove the convergence of the KKT points as the sample size tends to infinity. An inexact parallel proximal gradient descent ascent algorithm is proposed to solve this class of problems with the SAA. Numerical experiments demonstrate the effectiveness of the proposed algorithm and validate the convergence properties of the SAA approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03339 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Solutions of Two-stage Stochastic Minimax Problems Sun, Hailin Chen, Xiaojun Optimization and Control 90C15, 49K35, 90C47 This paper introduces a class of two-stage stochastic minimax problems where the first-stage objective function is nonconvex-concave while the second-stage objective function is strongly convex-concave. We establish properties of the second-stage minimax value function and solution functions, and characterize the existence and relationships among saddle points, minimax points, and KKT points. We apply the sample average approximation (SAA) to the class of two-stage stochastic minimax problems and prove the convergence of the KKT points as the sample size tends to infinity. An inexact parallel proximal gradient descent ascent algorithm is proposed to solve this class of problems with the SAA. Numerical experiments demonstrate the effectiveness of the proposed algorithm and validate the convergence properties of the SAA approach. |
| title | Solutions of Two-stage Stochastic Minimax Problems |
| topic | Optimization and Control 90C15, 49K35, 90C47 |
| url | https://arxiv.org/abs/2511.03339 |