Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/93329
Title: | Group sparse optimization via ℓp,q regularization | Authors: | Hu, Y Li, C Meng, K Qin, J Yang, X |
Issue Date: | 2017 | Source: | Journal of machine learning research, 2017, v. 18, no. 1, p. 1-52 | Abstract: | In this paper, we investigate a group sparse optimization problem via ℓp,q regularization in three aspects: theory, algorithm and application. In the theoretical aspect, by introducing a notion of group restricted eigenvalue condition, we establish an oracle property and a global recovery bound of order O(λ22−q) for any point in a level set of the ℓp,q regularization problem, and by virtue of modern variational analysis techniques, we also provide a local analysis of recovery bound of order O(λ2) for a path of local minima. In the algorithmic aspect, we apply the well-known proximal gradient method to solve the ℓp,q regularization problems, either by analytically solving some specific ℓp,q regularization subproblems, or by using the Newton method to solve general ℓp,q regularization subproblems. In particular, we establish a local linear convergence rate of the proximal gradient method for solving the ℓ1,q regularization problem under some mild conditions and by first proving a second-order growth condition. As a consequence, the local linear convergence rate of proximal gradient method for solving the usual ℓq regularization problem (0<q<1) is obtained. Finally in the aspect of application, we present some numerical results on both the simulated data and the real data in gene transcriptional regulation. | Keywords: | Group sparse optimization Lower-order regularization Nonconvex optimization Restricted eigenvalue condition Proximal gradient method Iterative thresholding algorithm Gene regulation network |
Publisher: | MIT Press | Journal: | Journal of machine learning research | ISSN: | 1532-4435 | EISSN: | 1533-7928 | Rights: | © 2017 Yaohua Hu, Chong Li, Kaiwen Meng, Jing Qin, and Xiaoqi Yang. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v18/15-651.html The following publication Hu, Y., Li, C., Meng, K., Qin, J., & Yang, X. (2017). Group sparse optimization via lp, q regularization. The Journal of Machine Learning Research, 18(1), 960-1011 is available at https://jmlr.org/papers/v18/15-651.html |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
15-651.pdf | 4.46 MB | Adobe PDF | View/Open |
Page views
47
Last Week
0
0
Last month
Citations as of May 5, 2024
Downloads
22
Citations as of May 5, 2024
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.