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 19 条
  • [1] [Anonymous], 2012, P 26 AAAI C
  • [2] [Anonymous], 2006, P 23 INT C MACH LEAR
  • [3] Sparse Representation of a Polytope and Recovery of Sparse Signals and Low-Rank Matrices
    Cai, T. Tony
    Zhang, Anru
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2014, 60 (01) : 122 - 132
  • [4] Chen YD, 2014, PR MACH LEARN RES, V32
  • [5] CHISTOV AL, 1984, LECT NOTES COMPUT SC, V176, P17
  • [6] Dvijotham K., 2010, NULLSPACE COND UNPUB
  • [7] A NULLSPACE ANALYSIS OF THE NUCLEAR NORM HEURISTIC FOR RANK MINIMIZATION
    Dvijotham, Krishnamurthy
    Fazel, Maryam
    [J]. 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 3586 - 3589
  • [8] Fazel M, 2001, P AMER CONTR CONF, P4734, DOI 10.1109/ACC.2001.945730
  • [9] Matrix Completion From a Few Entries
    Keshavan, Raghunandan H.
    Montanari, Andrea
    Oh, Sewoong
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2010, 56 (06) : 2980 - 2998
  • [10] EXACT LOW-RANK MATRIX RECOVERY VIA NONCONVEX SCHATTEN p-MINIMIZATION
    Kong, Lingchen
    Xiu, Naihua
    [J]. ASIA-PACIFIC JOURNAL OF OPERATIONAL RESEARCH, 2013, 30 (03)
12