ShanghaiTech University Knowledge Management System
| Convergence Rate Analysis of Proximal Iteratively Reweighted l1 Methods for lp Regularization Problems | |
| 2021-01-11 | |
| 状态 | 已发表 |
| 摘要 | In this paper, we focus on the local convergence rate analysis of the proximal iteratively reweighted l1 algorithms for solving lp regularization problems, which are widely applied for inducing sparse solutions. We show that if the Kurdyka- Lojasiewicz (KL) property is satisfied, the algorithm converges to a unique first-order stationary point; furthermore, the algorithm has local linear convergence or local sublinear convergence. The theoretical results we derived are much stronger than the existing results for iteratively reweighted l1 algorithms. |
| 关键词 | Kurdyka-Lojasiewicz property iteratively reweighted algorithm lp regularization convergence rate |
| DOI | arXiv:2007.05747 |
| 相关网址 | 查看原文 |
| 出处 | Arxiv |
| WOS记录号 | PPRN:10473932 |
| WOS类目 | Mathematics |
| 资助项目 | National Natural Science Foundation of China[12001367] |
| 文献类型 | 预印本 |
| 条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348429 |
| 专题 | 信息科学与技术学院 信息科学与技术学院_PI研究组_王浩组 信息科学与技术学院_硕士生 |
| 作者单位 | 1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 2.Univ Washington, Dept Math, Seattle, WA 98195, USA |
| 推荐引用方式 GB/T 7714 | Wang, Hao,Zeng, Hao,Wang, Jiashan. Convergence Rate Analysis of Proximal Iteratively Reweighted l1 Methods for lp Regularization Problems. 2021. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
修改评论
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。