Convergence rate analysis of proximal iteratively reweighted l1 methods for lp regularization problems

被引：0
|
作者：
Wang, Hao [1 ]
Zeng, Hao [1 ]
Wang, Jiashan [2 ]
机构：
[1] ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China
[2] Univ Washington, Dept Math, Seattle, WA 98195 USA
来源：
OPTIMIZATION LETTERS | 2023年 / 17卷 / 02期
基金：
中国国家自然科学基金; 上海市自然科学基金;
关键词：
Kurdyka-Lojasiewicz property; Iteratively reweighted algorithm; l(p) regularization; Convergence rate; MINIMIZATION; ALGORITHM; NONCONVEX; SPARSITY;
D O I：
10.1007/s11590-022-01907-4
中图分类号：
C93 [管理学]; O22 [运筹学];
学科分类号：
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
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 KurdykaLojasiewicz 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.
引用
收藏
页码：413 / 435
页数：23
相关论文
共 29 条
  • [1] An extrapolated iteratively reweighted l1 method with complexity analysis
    Wang, Hao
    Zeng, Hao
    Wang, Jiashan
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2022, 83 (03) : 967 - 997
  • [2] Relating lp regularization and reweighted l1 regularization
    Wang, Hao
    Zeng, Hao
    Wang, Jiashan
    Wu, Qiong
    OPTIMIZATION LETTERS, 2021, 15 (08) : 2639 - 2660
  • [3] Structural damage detection based on iteratively reweighted l1 regularization algorithm
    Zhou, Xiaoqing
    Hou, Rongrong
    Wu, Yuhan
    ADVANCES IN STRUCTURAL ENGINEERING, 2019, 22 (06) : 1479 - 1487
  • [4] Improved Convergence for l∞ and l1 Regression via Iteratively Reweighted Least Squares
    Ene, Alina
    Vladu, Adrian
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [5] FAR FIELD SPLITTING BY ITERATIVELY REWEIGHTED l1 MINIMIZATION
    Griesmaier, Roland
    Sylvester, John
    SIAM JOURNAL ON APPLIED MATHEMATICS, 2016, 76 (02) : 705 - 730
  • [6] Iterative Reweighted l1 and l1 Methods for Finding Sparse Solutions
    Wipf, David
    Nagarajan, Srikantan
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2010, 4 (02) : 317 - 329
  • [7] The convergence analysis of SpikeProp algorithm with smoothing L1/2 regularization
    Zhao, Junhong
    Zurada, Jacek M.
    Yang, Jie
    Wu, Wei
    NEURAL NETWORKS, 2018, 103 : 19 - 28
  • [8] AN l1 - lp DC REGULARIZATION METHOD FOR COMPRESSED SENSING
    Cao, Wenhe
    Ku, Hong-Kun
    JOURNAL OF NONLINEAR AND CONVEX ANALYSIS, 2020, 21 (09) : 1889 - 1901
  • [9] L1/2 Regularization: Convergence of Iterative Half Thresholding Algorithm
    Zeng, Jinshan
    Lin, Shaobo
    Wang, Yao
    Xu, Zongben
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2014, 62 (09) : 2317 - 2329
  • [10] Distributed ISAR imaging based on convolution and total variation reweighted l1 regularization
    Fu, Xiaoyao
    Wang, Yu
    He, Tingting
    Tian, Biao
    Xu, Shiyou
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2024, 45 (14) : 4653 - 4671
123