Line-search and Adaptive Step Sizes for Nonconvex-strongly-concave Minimax Optimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914256216129536 |
|---|---|
| author | Ma, Bohao Xiao, Nachuan Zhang, Junyu |
| author_facet | Ma, Bohao Xiao, Nachuan Zhang, Junyu |
| contents | In this paper, we propose a novel reformulation of the smooth nonconvex-strongly-concave (NC-SC) minimax problems that casts the problem as a joint minimization. We show that our reformulation preserves not only first-order stationarity, but also global and local optimality, second-order stationarity, and the Kurdyka-Łojasiewicz (KL) property, of the original NC-SC problem, which is substantially stronger than its nonsmooth counterpart in the literature. With these enhanced structures, we design a versatile parameter-free and nonmonotone line-search framework that does not require evaluating the inner maximization. Under mild conditions, global convergence rates can be obtained, and, with KL property, full sequence convergence with asymptotic rates is also established. In particular, we show our framework is compatible with the gradient descent-ascent (GDA) algorithm. By equipping GDA with Barzilai-Borwein (BB) step sizes and nonmonotone line-search, our method exhibits superior numerical performance against the compared benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10086 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Line-search and Adaptive Step Sizes for Nonconvex-strongly-concave Minimax Optimization Ma, Bohao Xiao, Nachuan Zhang, Junyu Optimization and Control 65K05, 90C47, 90C06 In this paper, we propose a novel reformulation of the smooth nonconvex-strongly-concave (NC-SC) minimax problems that casts the problem as a joint minimization. We show that our reformulation preserves not only first-order stationarity, but also global and local optimality, second-order stationarity, and the Kurdyka-Łojasiewicz (KL) property, of the original NC-SC problem, which is substantially stronger than its nonsmooth counterpart in the literature. With these enhanced structures, we design a versatile parameter-free and nonmonotone line-search framework that does not require evaluating the inner maximization. Under mild conditions, global convergence rates can be obtained, and, with KL property, full sequence convergence with asymptotic rates is also established. In particular, we show our framework is compatible with the gradient descent-ascent (GDA) algorithm. By equipping GDA with Barzilai-Borwein (BB) step sizes and nonmonotone line-search, our method exhibits superior numerical performance against the compared benchmarks. |
| title | Line-search and Adaptive Step Sizes for Nonconvex-strongly-concave Minimax Optimization |
| topic | Optimization and Control 65K05, 90C47, 90C06 |
| url | https://arxiv.org/abs/2601.10086 |