Global convergence of proximal iteratively reweighted algorithm

被引：16
作者：
Sun, Tao [1 ]
Jiang, Hao [2 ]
Cheng, Lizhi [1 ,3 ]
机构：
[1] Natl Univ Def Technol, Coll Sci, Changsha 410073, Hunan, Peoples R China
[2] Natl Univ Def Technol, Coll Comp, Changsha 410073, Hunan, Peoples R China
[3] Natl Univ Def Technol, State Key Lab High Performance Computat, Changsha 410073, Hunan, Peoples R China
来源：
JOURNAL OF GLOBAL OPTIMIZATION | 2017年 / 68卷 / 04期
基金：
美国国家科学基金会;
关键词：
Proximal iteratively reweighted algorithm; Kurdyka-Lojasiewicz function; Convergence analysis; Parallel splitting; Alternating updating; NONCONVEX; OPTIMIZATION; MINIMIZATION;
D O I：
10.1007/s10898-017-0507-z
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 investigate the convergence of the proximal iteratively reweighted algorithm for a class of nonconvex and nonsmooth problems. Such problems actually include numerous models in the area of signal processing and machine learning research. Two extensions of the algorithm are also studied. We provide a unified scheme for these three algorithms. With the Kurdyka-Lojasiewicz property, we prove that the unified algorithm globally converges to a critical point of the objective function.
引用
收藏
页码：815 / 826
页数：12
相关论文
共 50 条
  • [41] A simple convergence analysis of Bregman proximal gradient algorithm
    Zhou, Yi
    Liang, Yingbin
    Shen, Lixin
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2019, 73 (03) : 903 - 912
  • [42] Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum
    Kim, Junhyung Lyle
    Toulis, Panos
    Kyrillidis, Anastasios
    LEARNING FOR DYNAMICS AND CONTROL CONFERENCE, VOL 168, 2022, 168
  • [43] Iteratively reweighted unidirectional variational model for stripe non-uniformity correction
    Huang, Yongzhong
    He, Cong
    Fang, Houzhang
    Wang, Xiaoping
    INFRARED PHYSICS & TECHNOLOGY, 2016, 75 : 107 - 116
  • [44] Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems
    Mukhoty, Bhaskar
    Gopakumar, Govind
    Jain, Prateek
    Kar, Purushottam
    22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, 2019, 89 : 313 - 322
  • [45] Iteratively Linearized Reweighted Alternating Direction Method of Multipliers for a Class of Nonconvex Problems
    Sun, Tao
    Jiang, Hao
    Cheng, Lizhi
    Zhu, Wei
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, 66 (20) : 5380 - 5391
  • [46] FAST ITERATIVELY REWEIGHTED LEAST SQUARES FOR LP REGULARIZED IMAGE DECONVOLUTION AND RECONSTRUCTION
    Zhou, Xu
    Molina, Rafael
    Zhou, Fugen
    Katsaggelos, Aggelos K.
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 1783 - 1787
  • [47] Capri: Consensus Accelerated Proximal Reweighted Iteration for A Class of Nonconvex Minimizations
    Sun, Tao
    Li, Dongsheng
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2022, 34 (03) : 1066 - 1079
  • [48] GLOBAL CONVERGENCE RATE OF PROXIMAL INCREMENTAL AGGREGATED GRADIENT METHODS
    Vanli, N. D.
    Gurbuzbalaban, M.
    Ozdaglar, A.
    SIAM JOURNAL ON OPTIMIZATION, 2018, 28 (02) : 1282 - 1300
  • [49] Sparse dictionary learning by block proximal gradient with global convergence
    Zhu, Tao
    NEUROCOMPUTING, 2019, 367 : 226 - 235
  • [50] Completion of Structured Low-Rank Matrices via Iteratively Reweighted Least Squares
    Kummerle, Christian
    Verdun, Claudio M.
    2019 13TH INTERNATIONAL CONFERENCE ON SAMPLING THEORY AND APPLICATIONS (SAMPTA), 2019,
12345