Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.00810 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909670117998592 |
|---|---|
| author | Xu, Qing Xuan, Xiaohua |
| author_facet | Xu, Qing Xuan, Xiaohua |
| contents | In this paper, we propose an improved numerical algorithm for solving minimax problems based on nonsmooth optimization, quadratic programming and iterative process. We also provide a rigorous proof of convergence for our algorithm under some mild assumptions, such as gradient continuity and boundedness. Such an algorithm can be widely applied in various fields such as robust optimization, imbalanced learning, etc. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00810 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Robust Algorithm for Non-IID Machine Learning Problems with Convergence Analysis Xu, Qing Xuan, Xiaohua Artificial Intelligence Optimization and Control In this paper, we propose an improved numerical algorithm for solving minimax problems based on nonsmooth optimization, quadratic programming and iterative process. We also provide a rigorous proof of convergence for our algorithm under some mild assumptions, such as gradient continuity and boundedness. Such an algorithm can be widely applied in various fields such as robust optimization, imbalanced learning, etc. |
| title | A Robust Algorithm for Non-IID Machine Learning Problems with Convergence Analysis |
| topic | Artificial Intelligence Optimization and Control |
| url | https://arxiv.org/abs/2507.00810 |