Effective Proximal Methods for Non-convex Non-smooth Regularized Learning

被引:0
|
作者
Liang, Guannan [1 ]
Tong, Qianqian [1 ]
Ding, Jiahao [2 ]
Pan, Miao [2 ]
Bi, Jinbo [1 ]
机构
[1] Univ Connecticut, Storrs, CT 06269 USA
[2] Univ Houston, Houston, TX 77004 USA
基金
美国国家科学基金会;
关键词
Stochastic algorithm; proximal methods; arbitrary sampling; VARIABLE SELECTION;
D O I
10.1109/ICDM50108.2020.00043
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Non-convex non-smooth regularized learning problems play essential roles in sparse learning, and have drawn extensive attentions recently. We design a family of stochastic proximal gradient methods by applying arbitrary sampling to solve the empirical risk minimization problem with a non-convex and non-smooth regularizer. These methods draw mini-batches of training examples according to an arbitrary probability distribution when computing stochastic gradients. A unified analytic approach is developed to examine the convergence and computational complexity of these methods, allowing us to compare the different sampling schemes. We show that the independent sampling scheme tends to improve performance over the commonly-used uniform sampling scheme. Our new analysis also derives a tighter bound on convergence speed for the uniform sampling than the best one available so far. Empirical evaluations demonstrate that the proposed algorithms converge faster than the state of the art.
引用
收藏
页码:342 / 351
页数:10
相关论文
共 50 条
  • [21] ON A NEW SMOOTHING TECHNIQUE FOR NON-SMOOTH, NON-CONVEX OPTIMIZATION
    Yilmaz, Nurullah
    Sahiner, Ahmet
    NUMERICAL ALGEBRA CONTROL AND OPTIMIZATION, 2020, 10 (03): : 317 - 330
  • [22] Minimization of Non-smooth, Non-convex Functionals by Iterative Thresholding
    Bredies, Kristian
    Lorenz, Dirk A.
    Reiterer, Stefan
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2015, 165 (01) : 78 - 112
  • [23] A splitting bundle approach for non-smooth non-convex minimization
    Fuduli, A.
    Gaudioso, M.
    Nurminski, E. A.
    OPTIMIZATION, 2015, 64 (05) : 1131 - 1151
  • [24] Non-convex and non-smooth variational decomposition for image restoration
    Tang Liming
    Zhang Honglu
    He Chuanjiang
    Fang Zhuang
    APPLIED MATHEMATICAL MODELLING, 2019, 69 : 355 - 377
  • [25] KKT OPTIMALITY CONDITIONS IN NON-SMOOTH, NON-CONVEX OPTIMIZATION
    Sisarat, Nithirat
    Wangkeeree, Rabian
    Lee, Gue Myung
    JOURNAL OF NONLINEAR AND CONVEX ANALYSIS, 2018, 19 (08) : 1319 - 1329
  • [26] Minimization of Non-smooth, Non-convex Functionals by Iterative Thresholding
    Kristian Bredies
    Dirk A. Lorenz
    Stefan Reiterer
    Journal of Optimization Theory and Applications, 2015, 165 : 78 - 112
  • [27] Regularized bundle methods for convex and non-convex risks
    Do, Trinh-Minh-Tri
    Artieres, Thierry
    Journal of Machine Learning Research, 2012, 13 : 3539 - 3583
  • [28] A non-convex and non-smooth weighted image denoising model
    Fan, Huayu
    Feng, Qiqi
    Chen, Rui
    Cao, Xiangyang
    Pang, Zhi-Feng
    COMPUTERS & MATHEMATICS WITH APPLICATIONS, 2025, 187 : 85 - 105
  • [29] Regularized Bundle Methods for Convex and Non-Convex Risks
    Trinh-Minh-Tri Do
    Artieres, Thierry
    JOURNAL OF MACHINE LEARNING RESEARCH, 2012, 13 : 3539 - 3583
  • [30] Convergence guarantees for a class of non-convex and non-smooth optimization problems
    Khamaru, Koulik
    Wainwright, Martin J.
    Journal of Machine Learning Research, 2019, 20