On Globally Q-Linear Convergence of a Splitting Method for Group Lasso

被引：0
|
作者：
Dong Y.-D. [1 ]
Zhang H.-B. [2 ]
Gao H. [2 ,3 ]
机构：
[1] School of Mathematics and Statistics, Zhengzhou University, Zhengzhou
[2] College of Applied Sciences, Beijing University of Technology, Beijing
[3] College of Mathematics and Computational Science, Hunan First Normal University, Changsha
来源：
Journal of the Operations Research Society of China | 2018年 / 6卷 / 03期
基金：
中国国家自然科学基金;
关键词：
Group Lasso; Proximal gradient method; Q-linear rate of convergence; Splitting method;
D O I：
10.1007/s40305-017-0176-0
中图分类号：
学科分类号：
摘要：
In this paper, we discuss a splitting method for group Lasso. By assuming that the sequence of the step lengths has positive lower bound and positive upper bound (unrelated to the given problem data), we prove its Q-linear rate of convergence of the distance sequence of the iterates to the solution set. Moreover, we make comparisons with convergence of the proximal gradient method analyzed very recently. © 2017, Operations Research Society of China, Periodicals Agency of Shanghai University, Science Press, and Springer-Verlag GmbH Germany.
引用
收藏
页码：445 / 454
页数：9
相关论文
共 50 条
  • [41] Seagull: lasso, group lasso and sparse-group lasso regularization for linear regression models via proximal gradient descent
    Klosa, Jan
    Simon, Noah
    Westermark, Pal Olof
    Liebscher, Volkmar
    Wittenburg, Doerte
    BMC BIOINFORMATICS, 2020, 21 (01)
  • [42] Q-linear relations of specific families of multiple zeta values and the linear part of Kawashima's relation
    Hirose, Minoru
    Murahara, Hideki
    Onozuka, Tomokazu
    MANUSCRIPTA MATHEMATICA, 2021, 164 (3-4) : 455 - 465
  • [43] A globally convergent algorithm for lasso-penalized mixture of linear regression models
    Lloyd-Jones, Luke R.
    Nguyen, Hien D.
    McLachlan, Geoffrey J.
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2018, 119 : 19 - 38
  • [44] A Globally Convergent Matrix-Free Method for Constrained Equations and Its Linear Convergence Rate
    Sun, Min
    Liu, Jing
    ABSTRACT AND APPLIED ANALYSIS, 2014,
  • [45] The linear Steklov method for SDEs with non-globally Lipschitz coefficients: Strong convergence and simulation
    Diaz-Infante, S.
    Jerez, S.
    JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2017, 309 : 408 - 423
  • [46] Spherical q-linear Diophantine fuzzy aggregation information: Application in decision support systems
    Ashraf, Shahzaib
    Razzaque, Huzaira
    Naeem, Muhammad
    Botmart, Thongchai
    AIMS MATHEMATICS, 2023, 8 (03): : 6651 - 6681
  • [47] Global Linear Convergence in Operator Splitting Methods
    Banjac, Goran
    Goulart, Paul J.
    2016 IEEE 55TH CONFERENCE ON DECISION AND CONTROL (CDC), 2016, : 233 - 238
  • [48] Properties for Close-to-Convex and Quasi-Convex Functions Using q-Linear Operator
    Ali, Ekram E.
    El-Ashwah, Rabha M.
    Albalahi, Abeer M.
    Mohammed, Wael W.
    MATHEMATICS, 2025, 13 (06)
  • [49] On the Linear Convergence of the Approximate Proximal Splitting Method for Non-smooth Convex Optimization
    Kadkhodaie M.
    Sanjabi M.
    Luo Z.-Q.
    Journal of the Operations Research Society of China, 2014, 2 (2) : 123 - 141
  • [50] On the asymptotic properties of the group lasso estimator for linear models
    Nardi, Yuval
    Rinaldo, Alessandro
    ELECTRONIC JOURNAL OF STATISTICS, 2008, 2 : 605 - 633
12345