Convergence rate analysis of proximal iteratively reweighted ℓ _1 methods for ℓ _p regularization problems
Optimization Letters(2022)
摘要
In this paper, we focus on the local convergence rate analysis of the proximal iteratively reweighted ℓ _1 algorithms for solving ℓ _p regularization problems, which are widely applied for inducing sparse solutions. We show that if the Kurdyka–Łojasiewicz 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 ℓ _1 algorithms.
更多查看译文
关键词
Kurdyka–Łojasiewicz property,Iteratively reweighted algorithm,regularization,Convergence rate
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要