Two trust region type algorithms for solving nonconvex-strongly concave minimax problems
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909107399688192 |
|---|---|
| author | Yao, Tongliang Xu, Zi |
| author_facet | Yao, Tongliang Xu, Zi |
| contents | In this paper, we propose a Minimax Trust Region (MINIMAX-TR) algorithm and a Minimax Trust Region Algorithm with Contractions and Expansions(MINIMAX-TRACE) algorithm for solving nonconvex-strongly concave minimax problems. Both algorithms can find an $(ε, \sqrtε)$-second order stationary point(SSP) within $\mathcal{O}(ε^{-1.5})$ iterations, which matches the best well known iteration complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09807 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Two trust region type algorithms for solving nonconvex-strongly concave minimax problems Yao, Tongliang Xu, Zi Optimization and Control Machine Learning 90C47, 90C26, 90C30 In this paper, we propose a Minimax Trust Region (MINIMAX-TR) algorithm and a Minimax Trust Region Algorithm with Contractions and Expansions(MINIMAX-TRACE) algorithm for solving nonconvex-strongly concave minimax problems. Both algorithms can find an $(ε, \sqrtε)$-second order stationary point(SSP) within $\mathcal{O}(ε^{-1.5})$ iterations, which matches the best well known iteration complexity. |
| title | Two trust region type algorithms for solving nonconvex-strongly concave minimax problems |
| topic | Optimization and Control Machine Learning 90C47, 90C26, 90C30 |
| url | https://arxiv.org/abs/2402.09807 |