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：
上海市自然科学基金; 中国国家自然科学基金;
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 50 条
  • [1] Convergence analysis of iteratively reweighted l1 algorithms for computing the proximal operator of lP-norm
    Lin, Rongrong
    Li, Shimin
    Li, Zijia
    Liu, Yulan
    MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2025, 48 (01) : 386 - 396
  • [2] Relating lp regularization and reweighted l1 regularization
    Wang, Hao
    Zeng, Hao
    Wang, Jiashan
    Wu, Qiong
    OPTIMIZATION LETTERS, 2021, 15 (08) : 2639 - 2660
  • [3] Iteratively Reweighted l1 Approaches to Sparse Composite Regularization
    Ahmad, Rizwan
    Schniter, Philip
    IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2015, 1 (04) : 220 - 235
  • [4] 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
  • [5] Iterative reweighted methods for l1 - lp minimization
    Xiu, Xianchao
    Kong, Lingchen
    Li, Yan
    Qi, Houduo
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2018, 70 (01) : 201 - 219
  • [6] 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
  • [7] An extrapolated iteratively reweighted l1 method with complexity analysis
    Wang, Hao
    Zeng, Hao
    Wang, Jiashan
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2022, 83 (03) : 967 - 997
  • [8] Convergence of the reweighted l1 minimization algorithm for l2-lp minimization
    Chen, Xiaojun
    Zhou, Weijun
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2014, 59 (1-2) : 47 - 61
  • [9] FAR FIELD SPLITTING BY ITERATIVELY REWEIGHTED l1 MINIMIZATION
    Griesmaier, Roland
    Sylvester, John
    SIAM JOURNAL ON APPLIED MATHEMATICS, 2016, 76 (02) : 705 - 730
  • [10] The l1 penalized decoder and its reweighted LP
    Liu, Xishuo
    Draper, Stark C.
    Recht, Benjamin
    2012 50TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2012, : 1572 - 1579
12345