A p-SPHERICAL SECTION PROPERTY FOR MATRIX SCHATTEN-p QUASI-NORM MINIMIZATION

被引：0
|
作者：
Feng, Yifu [1 ]
Zhang, Min [2 ,3 ]
机构：
[1] Jilin Normal Univ, Coll Math, Siping 136000, Jilin, Peoples R China
[2] Chongqing Normal Univ, Sch Math Sci, Chongqing 401131, Peoples R China
[3] Curtin Univ, Sch Elec Engn Comp & Math Sci EECMS, Bentley, WA 6102, Australia
来源：
JOURNAL OF INDUSTRIAL AND MANAGEMENT OPTIMIZATION | 2020年 / 16卷 / 01期
关键词：
Low-rank matrix recovery; Schatten-p minimization; spherical section property; SPARSE REPRESENTATION; RANK; RECOVERY;
D O I：
10.3934/jimo.2018159
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
Low-rank matrix recovery has become a popular research topic with various applications in recent years. One of the most popular methods to dual with this problem for overcoming its NP-hardness is to relax it into some tractable optimization problems. In this paper, we consider a nonconvex relaxation, the Schatten-p quasi-norm minimization (0 < p < 1), and discuss conditions for the equivalence between the original problem and this nonconvex relaxation. Specifically, based on null space analysis, we propose a p-spherical section property for the exact and approximate recovery via the Schatten-p quasi-norm minimization (0 < p < 1).
引用
收藏
页码：397 / 407
页数：11
相关论文
共 50 条
  • [1] Performance guarantees for Schatten-p quasi-norm minimization in recovery of low-rank matrices
    Malek-Mohammadi, Mohammadreza
    Babaie-Zadeh, Massoud
    Skoglund, Mikael
    SIGNAL PROCESSING, 2015, 114 : 225 - 230
  • [2] Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization
    Shang, Fanhua
    Liu, Yuanyuan
    Cheng, James
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 2016 - 2022
  • [3] Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization
    Shang, Fanhua
    Liu, Yuanyuan
    Cheng, James
    ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 51, 2016, 51 : 620 - 629
  • [4] Discriminative low-rank graph preserving dictionary learning with Schatten-p quasi-norm regularization for image recognition
    Du, Haishun
    Zhao, Zhaolong
    Wang, Sheng
    Zhang, Fan
    NEUROCOMPUTING, 2018, 275 : 697 - 710
  • [5] LRR for Subspace Segmentation via Tractable Schatten-p Norm Minimization and Factorization
    Zhang, Hengmin
    Yang, Jian
    Shang, Fanhua
    Gong, Chen
    Zhang, Zhenyu
    IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (05) : 1722 - 1734
  • [6] Online Schatten quasi-norm minimization for robust principal component analysis
    Jia, Xixi
    Feng, Xiangchu
    Wang, Weiwei
    Huang, Hua
    Xu, Chen
    INFORMATION SCIENCES, 2019, 476 : 83 - 94
  • [7] Low-Rank Matrix Recovery via Modified Schatten-p Norm Minimization With Convergence Guarantees
    Zhang, Hengmin
    Qian, Jianjun
    Zhang, Bob
    Yang, Jian
    Gong, Chen
    Wei, Yang
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 3132 - 3142
  • [8] Traffic Data Imputation Based on Graph Regularization and Schatten-p Norm Minimization
    Chen X.
    Liang S.
    Ke J.
    Chen L.
    Hu Y.
    Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2022, 57 (06): : 1326 - 1333
  • [9] A Unified Convex Surrogate for the Schatten-p Norm
    Xu, Chen
    Lin, Zhouchen
    Zha, Hongbin
    THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 926 - 932
  • [10] On the Schatten p-quasi-norm minimization for low-rank matrix recovery
    Lai, Ming-Jun
    Liu, Yang
    Li, Song
    Wang, Huimin
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2021, 51 : 157 - 170
12345