Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2308.12359 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916770641608704 |
|---|---|
| author | Alcala, James K. Chow, Yat Tin Sunkula, Mahesh |
| author_facet | Alcala, James K. Chow, Yat Tin Sunkula, Mahesh |
| contents | This work introduces a moving anchor acceleration technique to extragradient algorithms for smooth structured minimax problems. The moving anchor is introduced as a generalization of the original algorithmic anchoring framework, i.e. the EAG method introduced in [32], in hope of further acceleration. We show that the optimal order of convergence in terms of worst-case complexity on the squared gradient, O(1/k2), is achieved by our new method (where k is the number of iterations). We have also extended our algorithm to a more general nonconvex-nonconcave class of saddle point problems using the framework of [14], which slightly generalizes [32]. We obtain similar order-optimal complexity results in this extended case. In both problem settings, numerical results illustrate the efficacy of our moving anchor algorithm variants, in particular by attaining the theoretical optimal convergence rate for first order methods, as well as suggesting a better optimized constant in the big O notation which surpasses the traditional fixed anchor methods in many cases. A proximal-point preconditioned version of our algorithms is also introduced and analyzed to match optimal theoretical convergence rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_12359 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Moving Anchor Extragradient Methods For Smooth Structured Minimax Problems Alcala, James K. Chow, Yat Tin Sunkula, Mahesh Optimization and Control 47N10 This work introduces a moving anchor acceleration technique to extragradient algorithms for smooth structured minimax problems. The moving anchor is introduced as a generalization of the original algorithmic anchoring framework, i.e. the EAG method introduced in [32], in hope of further acceleration. We show that the optimal order of convergence in terms of worst-case complexity on the squared gradient, O(1/k2), is achieved by our new method (where k is the number of iterations). We have also extended our algorithm to a more general nonconvex-nonconcave class of saddle point problems using the framework of [14], which slightly generalizes [32]. We obtain similar order-optimal complexity results in this extended case. In both problem settings, numerical results illustrate the efficacy of our moving anchor algorithm variants, in particular by attaining the theoretical optimal convergence rate for first order methods, as well as suggesting a better optimized constant in the big O notation which surpasses the traditional fixed anchor methods in many cases. A proximal-point preconditioned version of our algorithms is also introduced and analyzed to match optimal theoretical convergence rates. |
| title | Moving Anchor Extragradient Methods For Smooth Structured Minimax Problems |
| topic | Optimization and Control 47N10 |
| url | https://arxiv.org/abs/2308.12359 |