一类带MCP函数正则化问题的稳定性研究
Study on the Strong Metric Subregularity for a Class of Regularization Problems with the MCP Penalty Functions
DOI: 10.12677/pm.2024.144152, PDF,    科研立项经费支持
作者: 赵立斌：重庆交通大学数学与统计学院，重庆；李明华：重庆文理学院数学与大数据学院，重庆
关键词: MCP函数；次微分；图像导数；强度量次正则；MCP Function； Subdifferential； Graphical Derivative； Strong Metric Subregularity
摘要: 本文研究一类带极大极小凹惩罚(MCP)函数正则化问题，该模型由二次可微的损失函数和MCP函数组成。首先我们研究了MCP函数的邻近次微分和极限次微分，然后利用该次微分表达式和图像导数的运算法则，得到带MCP正则化问题目标函数次微分图像导数。最后，利用该图像导数表达式分别建立了该正则化问题次微分强度量次正则的充分条件和充要条件。
Abstract: In this paper, we study a class of regularization problems with the minimax concave penalty (MCP) function, which consists of a twice differentiable loss function and the MCP penalty function. First, we study the prox-regular subdifferential and limiting subdifferential of the MCP penalty function. Next, we obtain the graphical derivative of regularization problems with the MCP penalty function by using the subdifferential expression. Finally, we use the graphical derivative to establish a sufficient condition, a sufficient and necessary condition for the strong metric subregularity of subdifferential of the regularization problems, respectively.
文章引用：赵立斌, 李明华. 一类带MCP函数正则化问题的稳定性研究[J]. 理论数学, 2024, 14(4): 448-458. https://doi.org/10.12677/pm.2024.144152

参考文献

[1] Fan, J.Q. and Li, R. (2001) Variable Selection via Nonconcave Penalized Likelihood and Its Oracle Properties. Journal of the American Statistical Association, 96, 1348-1360. [Google Scholar] [CrossRef] 
[2] Zhang, C. (2012) Nearly Unbiased Variable Selection under Minimax Concave Penalty. The Annals of Statistics, 38, 894-942. [Google Scholar] [CrossRef] 
[3] Andriyana, Y., Fitriani, R., Tantular, B., et al. (2023) Modeling the Cigarette Consumption of Poor Households Using Penalized Zero-Inflated Negative Binomial Regression with Minimax Concave Penalty. Mathematics, 11, 3192. [Google Scholar] [CrossRef] 
[4] Kumar, P.P., Vamshi, R.H. and Sekhar, C.S. (2022) Iteratively Reweighted Minimax-Concave Penalty Minimization for Accurate Low-Rank Plus Sparse Matrix Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 8992-9010.
[5] Wang, S., Selesnick, W.I., Cai, G., et al. (2019) Synthesis Versus Analysis Priors via Generalized Minimax-Concave Penalty for Sparsity-Assisted Machinery fault Diagnosis. Mechanical Systems and Signal Processing, 127, 202-233. [Google Scholar] [CrossRef] 
[6] You, J., Jiao, Y., Lu, X., et al. (2019) A Nonconvex Model with Minimax Concave Penalty for Image Restoration. Journal of Scientific Computing, 78, 1063-1086. [Google Scholar] [CrossRef] 
[7] Cai, G., Selesnick, W.I., Wang, S., et al. (2018) Sparsity-Enhanced Signal Decomposition via Generalized Minimax-Concave Penalty for Gearbox Fault Diagnosis. Journal of Sound and Vibration, 432, 213-234. [Google Scholar] [CrossRef] 
[8] Shi, Y., Jiao, Y.L., et al. (2018) An Alternating Direction Method of Multipliers for MCP-penalized Regression with High-Dimensional Data. Acta Mathematica Sinica, English Series, 34, 1892-1906. [Google Scholar] [CrossRef] 
[9] Bello-Cruz, J.Y., Li, G.Y. and Nghia, T.T.A. (2021) On the Linear Convergence of Forward-Backward Splitting Method: Part I—Convergence Analysis. Journal of Optimization Theory and Applications, 188, 378-401. [Google Scholar] [CrossRef] 
[10] Drusvyatskiy, D. and Lewis, A.S. (2018) Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods. Mathematics of Operations Research, 43, 919-948. [Google Scholar] [CrossRef] 
[11] Hu, Y.H., Li, C., Meng, K.W. and Yang, X.Q. (2021) Linear Convergence of Inexact Descent Method and Inexact Proximal Gradient Algorithms for Lower-Order Regularization Problems. Journal of Global Optimization, 79, 853-883. [Google Scholar] [CrossRef] 
[12] Dontchev, A.L. and Rockafellar, R.T. (2009) Implicit Functions and Solution Mappings. A View from Variational Analysis. Springer, New York. [Google Scholar] [CrossRef] 
[13] Chieu, N.H., Hien, L.V., Nghia, T.T.A. and Tuan, H.A. (2021) Quadratic Growth and Strong Metric Subregularity of the Subdifferential via Subgradient Graphical Derivative. SIAM Journal on Optimization, 31, 545-568. [Google Scholar] [CrossRef] 
[14] Li, M.H., Meng, K.W. and Yang, X.Q. (2023) Variational Analysis of Kurdyka-Łojasiewicz Property, Exponent and Modulus. arXiv: 2308.15760.
[15] Bello-Cruz, Y., Li, G.Y. and Nghia, T.T.A. (2022) Quadratic Growth Conditions and Uniqueness of Optimalsolution to Lasso. Journal of Optimization Theory and Applications, 194, 167-190. [Google Scholar] [CrossRef] 
[16] Clarke, F.H., Ledyaev, Y.S., Stern, R.J. and Wolenski, P.R. (1998) Nonsmooth Analysis and Control Theory. Springer, New York.

为你推荐