Large-scale regression with non-convex loss and penalty

被引：16

作者：

Buccini, Alessandro ^{[1
]}

Cabrera, Omar De la Cruz ^{[2
]}

Donatelli, Marco ^{[3
]}

Martinelli, Andrea ^{[3
]}

Reichel, Lothar ^{[2
]}

机构：

[1] Univ Cagliari, Dept Math & Comp Sci, I-09124 Cagliari, Italy

[2] Kent State Univ, Dept Math Sci, Kent, OH 44242 USA

[3] Univ Insubria, Dept Sci & High Technol, I-22100 Como, Italy

来源：

APPLIED NUMERICAL MATHEMATICS | 2020年 / 157卷

关键词：

Regression; Regularization; Robustness; Non-convex Optimization; MINIMIZATION; REGULARIZATION; SHRINKAGE; ALGORITHM; SPARSITY;

D O I：

10.1016/j.apnum.2020.07.006

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

We describe a computational method for parameter estimation in linear regression, that is capable of simultaneously producing sparse estimates and dealing with outliers and heavy-tailed error distributions. The method used is based on the image restoration method proposed in Huang et al. (2017) [13]. It can be applied to problems of arbitrary size. The choice of certain parameters is discussed. Results obtained for simulated and real data are presented. (C) 2020 IMACS. Published by Elsevier B.V. All rights reserved.

引用

页码：590 / 601

页数：12

共 33 条

[1]

[Anonymous], 2009, Wiley Series in Probability and Statistics, DOI DOI 10.1002/9780470434697.CH7

[2]

[Anonymous], 2014, APPL LINEAR REGRESSI

[3]

Azzalini A., 2014, The Skew-Normal and Related Families, IMS monographs

[4] A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems [J].

Beck, Amir ;

Teboulle, Marc .

SIAM JOURNAL ON IMAGING SCIENCES, 2009, 2 (01) :183-202

[5] Modulus-based iterative methods for constrainedlp-lqminimization [J].

Buccini, A. ;

Pasha, M. ;

Reichel, L. .

INVERSE PROBLEMS, 2020, 36 (08)

[6] An lP-lq minimization method with cross-validation for the restoration of impulse noise contaminated images [J].

Buccini, Alessandro ;

Reichel, Lothar .

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2020, 375

[7]

Buccini A, 2019, J SCI COMPUT, V78, P1526, DOI 10.1007/s10915-018-0816-5

[8] Robust uncertainty principles:: Exact signal reconstruction from highly incomplete frequency information [J].

Candès, EJ ;

Romberg, J ;

Tao, T .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (02) :489-509

[9] Enhancing Sparsity by Reweighted l1 Minimization [J].

Candes, Emmanuel J. ;

Wakin, Michael B. ;

Boyd, Stephen P. .

JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2008, 14 (5-6) :877-905

[10]

Chan RH, 2014, LECT NOTES COMPUT SC, V8293, P78, DOI 10.1007/978-3-642-54774-4_4

← 1 2 3 4 →