Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107316
Title: | A regularized Newton method for ℓ𝑞-norm composite optimization problems | Authors: | Wu, Y Pan, S Yang, X |
Issue Date: | 2023 | Source: | SIAM journal on optimization, 2023, v. 33, no. 3, p. 1676-1706 | Abstract: | This paper is concerned with ℓ𝑞(0<𝑞<1) -norm regularized minimization problems with a twice continuously differentiable loss function. For this class of nonconvex and nonsmooth composite problems, many algorithms have been proposed to solve them, most of which are of the first-order type. In this work, we propose a hybrid of the proximal gradient method and the subspace regularized Newton method, called HpgSRN. The whole iterate sequence produced by HpgSRN is proved to have a finite length and to converge to an 𝐿 -type stationary point under a mild curve-ratio condition and the Kurdyka–Łojasiewicz property of the cost function; it converges linearly if a further Kurdyka–Łojasiewicz property of exponent 1/2 holds. Moreover, a superlinear convergence rate for the iterate sequence is also achieved under an additional local error bound condition. Our convergence results do not require the isolatedness and strict local minimality properties of the 𝐿 -stationary point. Numerical comparisons with ZeroFPR, a hybrid of proximal gradient method and quasi-Newton method for the forward-backward envelope of the cost function, proposed in [A. Themelis, L. Stella, and P. Patrinos, SIAM J. Optim., 28 (2018), pp. 2274–2303] for the ℓ𝑞 -norm regularized linear and logistic regressions on real data, indicate that HpgSRN not only requires much less computing time but also yields comparable or even better sparsities and objective function values. | Keywords: | ℓ𝑞-norm regularized composite optimization Global convergence KL property Local error bound Regularized Newton method Superlinear convergence rate |
Publisher: | Society for Industrial and Applied Mathematics | Journal: | SIAM journal on optimization | ISSN: | 1052-6234 | EISSN: | 1095-7189 | DOI: | 10.1137/22M1482822 | Rights: | Copyright © by SIAM. Unauthorized reproduction of this article is prohibited. The following publication Wu, Y., Pan, S., & Yang, X. (2023). A Regularized Newton Method for ℓ𝑞-Norm Composite Optimization Problems. SIAM Journal on Optimization, 33(3), 1676-1706 is available at https://doi.org/10.1137/22M1482822. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
22m1482822.pdf | 606.38 kB | Adobe PDF | View/Open |
Page views
7
Citations as of Jun 30, 2024
Downloads
6
Citations as of Jun 30, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.