Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Nonconvex Sparsity Optimization

被引:0
|
作者
Lu, Canyi [1 ]
Wei, Yunchao [2 ]
Lin, Zhouchen [3 ]
Yan, Shuicheng [1 ]
机构
[1] Natl Univ Singapore, Dept Elect & Comp Engn, Singapore, Singapore
[2] Beijing Jiaotong Univ, Inst Informat Sci, Beijing, Peoples R China
[3] Peking Univ, Sch EECS, Key Lab Machine Percept MOE, Beijing, Peoples R China
基金
新加坡国家研究基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes the Proximal Iteratively REweighted (PIRE) algorithm for solving a general problem, which involves a large body of nonconvex sparse and structured sparse related problems. Comparing with previous iterative solvers for nonconvex sparse problem, PIRE is much more general and efficient. The computational cost of PIRE in each iteration is usually as low as the state-of-the-art convex solvers. We further propose the PIRE algorithm with Parallel Splitting (PIRE-PS) and PIRE algorithm with Alternative Updating (PIRE-AU) to handle the multi-variable problems. In theory, we prove that our proposed methods converge and any limit solution is a stationary point. Extensive experiments on both synthesis and real data sets demonstrate that our methods achieve comparative learning performance, but are much more efficient, by comparing with previous nonconvex solvers.
引用
收藏
页码:1251 / 1257
页数:7
相关论文
共 50 条
  • [1] Proximal Linearized Iteratively Reweighted Algorithms for Nonconvex and Nonsmooth Optimization Problem
    Yeo, Juyeb
    Kang, Myeongmin
    [J]. AXIOMS, 2022, 11 (05)
  • [2] An extrapolated proximal iteratively reweighted method for nonconvex composite optimization problems
    Zhili Ge
    Zhongming Wu
    Xin Zhang
    Qin Ni
    [J]. Journal of Global Optimization, 2023, 86 : 821 - 844
  • [3] An extrapolated proximal iteratively reweighted method for nonconvex composite optimization problems
    Ge, Zhili
    Wu, Zhongming
    Zhang, Xin
    Ni, Qin
    [J]. JOURNAL OF GLOBAL OPTIMIZATION, 2023, 86 (04) : 821 - 844
  • [4] On an iteratively reweighted linesearch based algorithm for nonconvex composite optimization
    Bonettini, S.
    Pezzi, D.
    Prato, M.
    Rebegoldi, S.
    [J]. INVERSE PROBLEMS, 2023, 39 (06)
  • [5] Global convergence of proximal iteratively reweighted algorithm
    Tao Sun
    Hao Jiang
    Lizhi Cheng
    [J]. Journal of Global Optimization, 2017, 68 : 815 - 826
  • [6] Global convergence of proximal iteratively reweighted algorithm
    Sun, Tao
    Jiang, Hao
    Cheng, Lizhi
    [J]. JOURNAL OF GLOBAL OPTIMIZATION, 2017, 68 (04) : 815 - 826
  • [7] NonConvex Iteratively Reweighted Least Square Optimization in Compressive Sensing
    Chakraborty, Madhuparna
    Barik, Alaka
    Nath, Ravinder
    Dutta, Victor
    [J]. MATERIAL AND MANUFACTURING TECHNOLOGY II, PTS 1 AND 2, 2012, 341-342 : 629 - +
  • [8] On Iteratively Reweighted Algorithms for Nonsmooth Nonconvex Optimization in Computer Vision
    Ochs, Peter
    Dosovitskiy, Alexey
    Brox, Thomas
    Pock, Thomas
    [J]. SIAM JOURNAL ON IMAGING SCIENCES, 2015, 8 (01): : 331 - 372
  • [9] An Alternating Proximal Splitting Method with Global Convergence for Nonconvex Structured Sparsity Optimization
    Zhang, Shubao
    Qian, Hui
    Gong, Xiaojin
    [J]. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 2330 - 2336
  • [10] A fast proximal iteratively reweighted nuclear norm algorithm for nonconvex low-rank matrix minimization problems
    Ge, Zhili
    Zhang, Xin
    Wu, Zhongming
    [J]. APPLIED NUMERICAL MATHEMATICS, 2022, 179 : 66 - 86