Abstract
In this paper, we study the low-rank matrix optimization problem, where the loss function is smooth but not necessarily convex, and the penalty term is a nonconvex (folded concave) continuous relaxation of the rank function. Firstly, we give the closed-form singular value shrinkage thresholding operators for several matrix-valued folded concave penalty functions. Secondly, we adopt a singular value shrinkage thresholding (SVST) algorithm for the nonconvex low-rank matrix optimization problem, and prove that the proposed SVST algorithm converges to a stationary point of the problem. Furthermore, we show that the limit point satisfies a global necessary optimality condition which can exclude too many stationary points even local minimizers in order to refine the solutions. We conduct a large number of numeric experiments to test the performance of SVST algorithm on the randomly generated low-rank matrix completion problem, the real 2D and 3D image recovery problem and the multivariate linear regression problem. Numerical results show that SVST algorithm is very competitive for low-rank matrix optimization problems in comparison with some state-of-the-art algorithms.
Similar content being viewed by others
Data availibility
Data will be made available on reasonable request.
References
Attouch, H., Bolte, J., Svaiter, B.F.: Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods. Math. Program. Ser. A 137, 91–129 (2013)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183–202 (2009)
Beck, A., Hallak, N.: Optimization problems involving group sparsity terms. Math. Program. 178, 39–67 (2019)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. Ser. A 146, 459–494 (2014)
Cai, J., Candès, E., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
Candès, E., Plan, Y.: Tight Oracle bounds for low-rank matrix recovery from a minimal number of noisy random measurements. IEEE Trans. Inf. Theory 57(4), 2342–2359 (2011)
Candès, E., Tao, T.: The power of convex relaxation: near-optimal matrix completion. IEEE Trans. Inf. Theory 56(5), 2053–2080 (2010)
Clarke, F.H.: Optimization and Nonsmooth Analysis. SIAM Publisher, New York (1990)
Cui, A., Peng, J., Li, H., Zhang, C., Yu, Y.: Corrigendum to “Affine matrix rank minimization problem via non-convex fraction function penalty” [J. Comput. Appl. Math. 336 (2018) 353-374]. J. Comput. Appl. Math. 352(15): 478–485
Drineas, P., Kannan, R., Mahoney, M.: Fast Monte Carlo algorithms for matrices II: computing low-rank approximations to a matrix. SIAM J. Comput. 36(1), 158–183 (2006)
Fan, J., Li, R.: Variable selection via nonconcave penalized likelihood and its oracle properties. J. Am. Stat. Assoc. 96(456), 1348–1360 (2001)
Fazel, M.: Matrix rank minimization with applications. PhD thesis, Stanford University (2002)
Foucart, S., Lai, M.-J.: Sparsest solutions of underdetermined linear systems via \(\ell _q\) minimization for \(0 < q \le 1\). Appl. Comput. Harmon. A. 26, 395–407 (2009)
Gong, P., Zhang, C., Lu, Z., Huang, J., Ye, J.: A general iterative shrinkage and thresholding algorithm for non-convex regularized optimization problems. In: Proceedings of the 30th International Conference on International Conference on Machine Learning (ICML’13), 28(2), pp. 37-45 (2013)
Gu, S., **e, Q., Meng, D., et al.: Weighted nuclear norm minimization and its applications to low level vision. Int. J. Comput. Vis. 121(2), 183–208 (2017)
He, L., Wang, Y., **ang, Z.: Support driven wavelet frame-based image deblurring. Inf. Sci. 479, 250–269 (2019)
Huang, J., Jiao, Y., **, B., Liu, J., Lu, X., Yang, C.: A unified primal dual active set algorithm for nonconvex sparse recovery. Stat. Sci. 36, 215–238 (2021)
**, Z.F., Wan, Z., Jiao, Y., Lu, X.: An alternating direction method with continuation for nonconvex low rank minimization. J. Sci. Comput. 66(2), 849–869 (2016)
Lai, M.-J., Xu, Y., Yin, W.: Improved iteratively rewighted least squares for unconstrained smoothed \(\ell _p\) minimization. SIAM J. Numer. Anal. 51(2), 927–957 (2013)
Lee, C., Lam, E.: Computationally efficient truncated nuclear norm minimization for high dynamic range imaging. IEEE Trans. Image Process. 25(9), 4145–4157 (2016)
Li, Y., Shang, K., Huang, Z.: A singular value p-shrinkage thresholding algorithm for low rank matrix recovery. Comput. Optim. Appl. 73, 453–476 (2019)
Liu, Y., Sun, D., Toh, K.-C.: An implementable proximal point algorithmic framework for nuclear norm minimization. Math. Program. 133(1–2), 399–436 (2012)
Lu, C., Zhu, C., Xu, C., Yan, S., Lin, Z.: Generalized singular value thresholding. In: Proceedings of the AAAI Conference on Artificial Intelligence 29(1), 1805–1811 (2015)
Lu, Z., Zhang, Y., Liu, X.: Penalty decomposition methods for rank minimization. Optim. Methods Softw. 30, 531–558 (2015)
Lu, Z., Zhang, Y., Lu, J.: \(\ell _p\) regularized low-rank approximation via iterative reweighted singular value minimization. Comput. Optim. Appl. 68, 619–642 (2017)
Ma, S., Goldfarb, D., Chen, L.: Fixed point and Bregman iterative methods for matrix rank minimization. Math. Program. 128(1–2), 321–353 (2011)
Ma, T., Lou, Y., Huang, T.: Truncated \(\ell _{1-2}\) models for sparse recovery and rank minimization. SIAM J. Imaging Sci. 10(3), 1346–1380 (2017)
Marjanovic, G., Solo, V.: On \(\ell _q\) optimization and matrix completion. IEEE Trans. Signal Process. 60(11), 5714–5724 (2012)
Oymak, S., Hassibi, B.: New null space results and recovery thresholds for matrix rank minimization. Eprint Arxiv 58(4), 766–773 (2010)
Pan, L., Chen, X.: Group sparse optimization for images recovery using capped folded concave functions. SIAM J. Imaging Sci. 14(1), 1–25 (2021)
Peng, D., **u, N., Yu, J.: \(S_{1/2}\) regularization methods and fixed point algorithms for affine rank minimization problems. Comput. Optim. Appl. 67, 543–569 (2017)
Peng, D., **u, N., Yu, J.: Global optimality conditions and fixed point continuation algorithm for non-Lipschitz \(\ell _{p}\) regularized matrix minimization. Sci China Math 61, 1139–1152 (2018)
Recht, B., Fazel, M., Parrilo, P.A.: Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev. 52(3), 471–501 (2010)
Recht, B., Xu, W., Hassibi, B.: Null space conditions and thresholds for rank minimization. Math. Program. 127(1), 175–202 (2011)
Rockafellar, R., Wets, R.-J.: Variational Analysis. Springer, Berlin (1998)
Su, X., Wang, Y., Kang, X., Tao, R.: Nonconvex truncated nuclear norm minimization based on adaptive bisection method. IEEE Trans. Circuits Syst. Video Technol. 29(11), 3159–3172 (2019)
Tseng, P.: Approximation accuracy, gradient methods, and error bound for structured convex optimization. Math. Program. Ser. B 125, 263–295 (2010)
Tütüncü, R., Toh, K.-C., Todd, M.: Solving semidefinite-quadratic-linear programs using SDPT3. Math. Program. 95(2), 189–217 (2003)
Toh, K.-C., Yun, S.: An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems. Pac. J. Optim. 6(3), 615–640 (2010)
Wang, S., Liu, D., Zhang, Z.: Nonconvex relaxation approaches to robust matrix recovery. In: The 23rd international conference on artificial intelligence in 2013 (IJCAI-2013), pp. 1764-1770 (2013)
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wang, Z., Wang, W., Wang, J., Chen, S.: Fast and efficient algorithm for matrix completion via closed-form \(2/3\)-thresholding operator. Neurocomputing 330, 212–222 (2019)
Wang, W., Zhang, F., Wang, J.: Low-rank matrix recovery via regularized nuclear norm minimization. Appl. Comput. Harmon. A. 54, 1–19 (2021)
**ao, Y., **, Z.: An alternating direction method for linear-constrained matrix nuclear norm minimization. Numer. Linear Algebra Appl. 19(3), 541–554 (2012)
Yang, J., Yuan, X.: Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization. Math. Comput. 82(281), 301–329 (2013)
Yu, Q., Zhang, X.: A smoothing proximal gradient algorithm for matrix rank minimization problem. Comput. Optim. Appl. 81, 519–538 (2022)
Zhang, C.: Nearly unbiased variable selection under minimax concave penalty. Ann. Stat. 38(2), 894–942 (2010)
Zhang, T.: Analysis of multi-stage convex relaxation for sparse regularization. J. Mach. Learn. Res. 11, 1081–1107 (2010)
Acknowledgements
This work is supported by the National Natural Science Foundation of China (12261020, 11861020), the Guizhou Provincial Science and Technology Program (ZK[2021]009), the Growth Project of Education Department of Guizhou Province for Young Talents in Science and Technology ([2018]121), and the Research Foundation for Postgraduates of Guizhou Province (YJSCXJH[2020]085).
The authors are deeply grateful to the three anonymous reviewers for their valuable suggestions and comments that help us to revise the paper into the present form.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, X., Peng, D. & Su, Y. A singular value shrinkage thresholding algorithm for folded concave penalized low-rank matrix optimization problems. J Glob Optim 88, 485–508 (2024). https://doi.org/10.1007/s10898-023-01322-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-023-01322-8
Keywords
- Low-rank matrix optimization
- Matrix completion problem
- Nonconvex continuous relaxation
- Singular value shrinkage thresholding algorithm