Convergence rate analysis of proximal iteratively reweighted l1 methods for lp regularization problems

被引：0

作者：

Wang, Hao ^{[1
]}

Zeng, Hao ^{[1
]}

Wang, Jiashan ^{[2
]}

机构：

[1] ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China

[2] Univ Washington, Dept Math, Seattle, WA 98195 USA

来源：

OPTIMIZATION LETTERS | 2023年 / 17卷 / 02期

基金：

上海市自然科学基金; 中国国家自然科学基金;

关键词：

Kurdyka-Lojasiewicz property; Iteratively reweighted algorithm; l(p) regularization; Convergence rate; MINIMIZATION; ALGORITHM; NONCONVEX; SPARSITY;

D O I：

10.1007/s11590-022-01907-4

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

In this paper, we focus on the local convergence rate analysis of the proximal iteratively reweighted l(1) algorithms for solving l(p) regularization problems, which are widely applied for inducing sparse solutions. We show that if the KurdykaLojasiewicz property is satisfied, the algorithm converges to a unique first-order stationary point; furthermore, the algorithm has local linear convergence or local sublinear convergence. The theoretical results we derived are much stronger than the existing results for iteratively reweighted l(1) algorithms.

引用

页码：413 / 435

页数：23

共 50 条

[31] L1/2 regularization learning for smoothing interval neural networks: Algorithms and convergence analysis
Yang, Dakun
Liu, Yan
NEUROCOMPUTING, 2018, 272 : 122 - 129
[32] Solving l1 Regularization Problems With Piecewise Linear Losses
Kato, Kengo
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2010, 19 (04) : 1024 - 1040
[33] Error analysis of reweighted l1 greedy algorithm for noisy reconstruction
Zhu, Jiehua
Li, Xiezhang
Arroyo, Fangjun
Arroyo, Edward
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2015, 286 : 93 - 101
[34] Speech Compressive Sensing with l1-minimzation and Iteratively Reweighted Least Squares-lp-minimization: A comparative Study
Derouaz, Wafa
Merazi-Meksen, Thouraya
2017 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING - BOUMERDES (ICEE-B), 2017,
[35] Iteratively Reweighted Least Squares Algorithms for L1-Norm Principal Component Analysis
Park, Young Woong
Klabjan, Diego
2016 IEEE 16TH INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2016, : 430 - 438
[36] Convergence of weak solutions of elliptic problems with datum in L1
Aparicio, Antonio J. Martinez
ELECTRONIC JOURNAL OF QUALITATIVE THEORY OF DIFFERENTIAL EQUATIONS, 2023, (21) : 1 - 13
[37] INFLUENCE OF DESIGN ON THE RATE OF CONVERGENCE TO NORMALITY IN L1 REGRESSION
HALL, P
WELSH, AH
MATHEMATICAL PROCEEDINGS OF THE CAMBRIDGE PHILOSOPHICAL SOCIETY, 1989, 106 : 355 - 368
[38] X-Rays Tomographic Reconstruction Images using Proximal Methods based on L1 Norm and TV Regularization
Allag, Aicha
Drai, Redouane
Benammar, Abdessalem
Boutkedjirt, Tarek
PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING IN DATA SCIENCES (ICDS2017), 2018, 127 : 236 - 245
[39] Noise robust image clustering based on reweighted low rank tensor approximation and l1/2 regularization
Madathil, Baburaj
George, Sudhish N.
SIGNAL IMAGE AND VIDEO PROCESSING, 2021, 15 (02) : 341 - 349
[40] Data reconstruction using iteratively reweighted L1-principal component analysis for an electronic nose system
Jeon, Hong-Min
Lee, Je-Yeol
Jeong, Gu-Min
Choi, Sang-Il
PLOS ONE, 2018, 13 (07):

← 1 2 3 4 5 →