Convergence of multi-block Bregman ADMM for nonconvex composite problems

被引:0
|
作者
Fenghui Wang
Wenfei Cao
Zongben Xu
机构
[1] Xi’an Jiaotong University,School of Mathematics and Statistics
[2] Luoyang Normal University,Department of Mathematics
[3] Shaanxi Normal University,School of Mathematics and Information Science
来源
关键词
nonconvex regularization; alternating direction method; subanalytic function; K-L inequality; Bregman distance;
D O I
暂无
中图分类号
学科分类号
摘要
The alternating direction method with multipliers (ADMM) is one of the most powerful and successful methods for solving various composite problems. The convergence of the conventional ADMM (i.e., 2-block) for convex objective functions has been stated for a long time, and its convergence for nonconvex objective functions has, however, been established very recently. The multi-block ADMM, a natural extension of ADMM, is a widely used scheme and has also been found very useful in solving various nonconvex optimization problems. It is thus expected to establish the convergence of the multi-block ADMM under nonconvex frameworks. In this paper, we first justify the convergence of 3-block Bregman ADMM. We next extend these results to the N-block case (N ≥ 3), which underlines the feasibility of multi-block ADMM applications in nonconvex settings. Finally, we present a simulation study and a real-world application to support the correctness of the obtained theoretical assertions.
引用
收藏
相关论文
共 50 条
  • [31] A linear algebra perspective on the random multi-block ADMM: the QP case
    Stefano Cipolla
    Jacek Gondzio
    Calcolo, 2023, 60
  • [32] Multi-block ADMM for big data optimization in modern communication networks
    Liu, Lanchao
    Han, Zhu
    Journal of Communications, 2015, 10 (09): : 666 - 676
  • [33] Convergence for nonconvex ADMM, with applications to CT imaging
    Barber, Rina Foygel
    Sidky, Emil Y.
    JOURNAL OF MACHINE LEARNING RESEARCH, 2024, 25
  • [34] Global Convergence of ADMM in Nonconvex Nonsmooth Optimization
    Wang, Yu
    Yin, Wotao
    Zeng, Jinshan
    JOURNAL OF SCIENTIFIC COMPUTING, 2019, 78 (01) : 29 - 63
  • [35] Global Convergence of ADMM in Nonconvex Nonsmooth Optimization
    Yu Wang
    Wotao Yin
    Jinshan Zeng
    Journal of Scientific Computing, 2019, 78 : 29 - 63
  • [36] An extended proximal ADMM algorithm for three-block nonconvex optimization problems
    Zhang, Chun
    Song, Yongzhong
    Cai, Xingju
    Han, Deren
    JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2021, 398 (398)
  • [37] Convergence and Applications of ADMM on the Multi-convex Problems
    Wang, Junxiang
    Zhao, Liang
    ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2022, PT II, 2022, 13281 : 30 - 43
  • [38] A multi-parameter parallel ADMM for multi-block linearly constrained separable convex optimization
    Shen, Yuan
    Gao, Qianming
    Yin, Xue
    APPLIED NUMERICAL MATHEMATICS, 2022, 171 : 369 - 388
  • [39] A partial PPA block-wise ADMM for multi-block linearly constrained separable convex optimization
    Shen, Yuan
    Zhang, Xingying
    Zhang, Xiayang
    OPTIMIZATION, 2021, 70 (03) : 631 - 657
  • [40] Linearized symmetric multi-block ADMM with indefinite proximal regularization and optimal proximal parameter
    Xiaokai Chang
    Jianchao Bai
    Dunjiang Song
    Sanyang Liu
    Calcolo, 2020, 57