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] Global convergence of a proximal linearized algorithm for difference of convex functions
    Souza, Joao Carlos O.
    Oliveira, Paulo Roberto
    Soubeyran, Antoine
    OPTIMIZATION LETTERS, 2016, 10 (07) : 1529 - 1539
  • [42] Global convergence of a proximal linearized algorithm for difference of convex functions
    João Carlos O. Souza
    Paulo Roberto Oliveira
    Antoine Soubeyran
    Optimization Letters, 2016, 10 : 1529 - 1539
  • [43] Iteratively reweighted 1 algorithms with extrapolation
    Yu, Peiran
    Pong, Ting Kei
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2019, 73 (02) : 353 - 386
  • [44] ON THE CONVERGENCE OF ALTERNATING MINIMIZATION FOR CONVEX PROGRAMMING WITH APPLICATIONS TO ITERATIVELY REWEIGHTED LEAST SQUARES AND DECOMPOSITION SCHEMES
    Beck, Amir
    SIAM JOURNAL ON OPTIMIZATION, 2015, 25 (01) : 185 - 209
  • [45] 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
  • [46] ITERATIVELY REWEIGHTED FGMRES AND FLSQR FOR SPARSE RECONSTRUCTION
    Gazzola, Silvia
    Nagy, James G.
    Landman, Malena Sabate
    SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2021, 43 (05): : S47 - S69
  • [47] 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
  • [48] MSE analysis of the iteratively reweighted least squares algorithm when applied to M estimators
    Kalyani, Sheetal
    Giridhar, K.
    GLOBECOM 2007: 2007 IEEE GLOBAL TELECOMMUNICATIONS CONFERENCE, VOLS 1-11, 2007, : 2873 - +
  • [49] Efficient Iteratively Reweighted LASSO Algorithm for Cross-Products Penalized Sparse Solutions
    Luengo, David
    Via, Javier
    Trigano, Tom
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 2045 - 2049
  • [50] Iteratively Reweighted Compressive Sensing Based Algorithm for Spectrum Cartography in Cognitive Radio Networks
    Jayawickrama, B. A.
    Dutkiewicz, E.
    Oppermann, I.
    Mueck, M.
    2014 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2014, : 719 - 724
12345