Abstract
Rank regularized minimization problem is an ideal model for the low-rank matrix completion/recovery problem. The matrix factorization approach can transform the high-dimensional rank regularized problem to a low-dimensional factorized column-sparse regularized problem. The latter can greatly facilitate fast computations in applicable algorithms, but needs to overcome the simultaneous non-convexity of the loss and regularization functions. In this paper, we consider the factorized column-sparse regularized model. Firstly, we optimize this model with bound constraints, and establish a certain equivalence between the optimized factorization problem and rank regularized problem. Further, we strengthen the optimality condition for stationary points of the factorization problem and define the notion of strong stationary point. Moreover, we establish the equivalence between the factorization problem and its nonconvex relaxation in the sense of global minimizers and strong stationary points. To solve the factorization problem, we design two types of algorithms and give an adaptive method to reduce their computation. The first algorithm is from the relaxation point of view and its iterates own some properties from global minimizers of the factorization problem after finite iterations. We give some analysis on the convergence of its iterates to a strong stationary point. The second algorithm is designed for directly solving the factorization problem. We improve the PALM algorithm introduced by Bolte et al. (Math Program Ser A 146:459–494, 2014) for the factorization problem and give its improved convergence results. Finally, we conduct numerical experiments to show the promising performance of the proposed model and algorithms for low-rank matrix completion.
Similar content being viewed by others
References
West, J.D., Wesley-Smith, I., Bergstrom, C.T.: A recommendation system based on hierarchical clustering of an article-level citation network. IEEE Trans. Big Data 2(2), 113–123 (2016)
Liu, Z., Vandenberghe, L.: Interior-point method for nuclear norm approximation with application to system identification. SIAM J. Matrix Anal. Appl. 31, 1235–1256 (2009)
Liu, Q., Lai, Z., Zhou, Z., Kuang, F., Jin, Z.: A truncated nuclear norm regularization method based on weighted residual error for matrix completion. IEEE Trans. Image Process. 25(1), 316–330 (2016)
Cabral, R., Torre, F.D., Costeira, J.P., Bernardino, A.: Matrix completion for weakly-supervised multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. 37(1), 121–135 (2015)
Fan, J., Chow, T.W.S.: Exactly robust kernel principal component analysis. IEEE Trans. Neural Netw. Learn. Syst. 31(3), 749–761 (2020)
Huber, P.J.: Robust regression: asymptotics, conjectures and Monte Carlo. Ann. Stat. 5(1), 799–821 (1973)
Koenker, R., Kevin, F.H.: Quantile regression. J. Econ. Perspect. 15(4), 143–156 (2001)
Srebro, N., Shraibman, A.: Rank, trace-norm and max-norm. In: Learning theory, pp. 545–560. Springer, Berlin (2005)
Gu, S., Zhang, L., Zuo, W., Feng, X.: Weighted nuclear norm minimization with application to image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2862–2869 (2014)
Hu, Y., Zhang, D., Ye, J., Li, X., He, X.: Fast and accurate matrix completion via truncated nuclear norm regularization. IEEE Trans. Pattern Anal. Mach. Intell. 35(9), 2117–2130 (2013)
Shang, F., Liu, Y., Cheng, J.: Scalable algorithms for tractable schatten quasi-norm minimization. In Proceedings of AAAI conference on artificial intelligence, 2016–2022 (2016)
Cai, J.-F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
Toh, K.-C., Yun, S.: An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems. Pac. J. Optim. 6(15), 615–640 (2010)
Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2009)
Cai, T.T., Zhou, W.-X.: Matrix completion via max-norm constrained optimization. Electron. J. Stat. 10(1), 1493–1525 (2016)
Fang, E.X., Liu, H., Toh, K.-C., Zhou, W.-X.: Max-norm optimization for robust matrix recovery. Math. Program. 167(1), 5–35 (2018)
Salakhutdinov, R., Srebro, N.: Collaborative filtering in a non-uniform world: learning with the weighted trace norm. Adv. Neural Inf. Process. Syst. 23, 1 (2010)
Yao, Q., Kwok, J.T., Wang, T., Liu, T.-Y.: Large-scale low-rank matrix learning with nonconvex regularizers. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2628–2643 (2018)
Fan, J., Ding, L., Chen, Y., Udell, M.: Factor group-sparse regularization for efficient low-rank matrix recovery. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Tao, T., Qian, Y., Pan, S.: Column \(\ell _{2,0}\)-norm regularized factorization model of low-rank matrix recovery and its computation. SIAM J. Optim. 32(2), 959–988 (2022)
Peleg, D., Meir, R.: A bilinear formulation for vector sparsity optimization. Signal Process. 88(2), 375–389 (2008)
Fan, J., Li, R.: Variable selection via nonconvave penalized likelihood and its oracle properties. J. Am. Stat. Assoc. 96(456), 1348–1360 (2001)
Zhang, C.-H.: Nearly unbiased variable selection under minimax concave penalty. Ann. Stat. 38(2), 894–942 (2010)
Bian, W., Chen, X.: A smoothing proximal gradient algorithm for nonsmooth convex regression with cardinality penalty. SIAM J. Numer. Anal. 58(1), 858–883 (2020)
Le Thi, H.A., Pham Dinh, T., Le, H.M., Vo, X.T.: DC approximation approaches for sparse optimization. Eur. J. Oper. Res. 244(1), 26–46 (2015)
Li, W., Bian, W., Toh, K.-C.: Difference-of-convex algorithms for a class of sparse group \(\ell _0\) regularized optimization problems. SIAM J. Optim. 32(3), 1614–1641 (2022)
Soubies, E., Blanc-Féraud, L., Aubert, G.: A unified view of exact continuous penalties for \(\ell _2\)-\(\ell _0\) minimization. SIAM J. Optim. 27(3), 2034–2060 (2017)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146(1–2), 459–494 (2014)
Pock, T., Sabach, S.: Inertial proximal alternating linearized minimization (iPALM) for nonconvex and nonsmooth problems. SIAM J. Imaging Sci. 9, 1756–1787 (2016)
Xu, Y., Yin, W.: A globally convergent algorithm for nonconvex optimization based on block coordinate update. J. Sci. Comput. 72, 700–734 (2017)
Phan, D.N., Le Thi, H.A.: DCA based algorithm with extrapolation for nonconvex nonsmooth optimization (2021). arXiv:2106.04743v1
Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis. Springer, Berlin (1998)
Mordukhovich, B.S.: Variational Analysis and Generalized Differentiation I: Basic Theory. Springer, Berlin (2006)
Attouch, H., Bolte, J., Redont, P., Soubeyran, A.: Proximal alternating minimization and projection methods for nonconvex problems: an approach based on the Kurdyka-Łojasiewicz inequality. Math. Oper. Res. 35(2), 438–457 (2010)
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. 137(1–2), 91–129 (2013)
Ruszczyński, A.: Nonlinear Optimization. Princeton University Press, Princeton (2006)
Yang, L., Pong, T.K., Chen, X.: A non-monotone alternating updating method for a class of matrix factorization problems. SIAM J. Optim. 28(4), 3402–3430 (2018)
Penot, J.-P.: Calculus without Derivatives. Springer, New York (2013)
Pang, J.-S., Razaviyayn, M., Alvarado, A.: Computing B-stationary points of nonsmooth DC programs. Math. Oper. Res. 42(1), 95–118 (2017)
Attouch, H., Bolte, J.: On the convergence of the proximal algorithm for nonsmooth functions involving analytic features. Math. Program. 116(1–2), 5–16 (2009)
Yu, Y.-L.: On decomposing the proximal map. In: Burges, C.J., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 26, pp. 91–99. Curran Associates, Inc. (2013)
Hastie, T., Mazumder, R., Lee, J.D., Zadeh, R.: Matrix completion and low-rank SVD via fast alternating least squares. J. Mach. Learn. Res. 16(1), 3367–3402 (2015)
Acknowledgements
Funding
Part of this work was done while Wenjing Li was with Department of Mathematics, National University of Singapore. The research of Wenjing Li is supported by the National Natural Science Foundation of China Grant (No. 12301397) and the China Postdoctoral Science Foundation Grant (No. 2023M730876). The research of Wei Bian is supported by the National Natural Science Foundation of China Grants (No. 12271127, 62176073), and the Fundamental Research Funds for Central Universities of China (HIT.OCEF.2024050, 2022FRFK060017). The research of Kim-Chuan Toh is supported by the Ministry of Education, Singapore, under its Academic Research Fund Tier 3 grant call (MOE-2019-T3-1-010).
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
Li, W., Bian, W. & Toh, KC. On solving a rank regularized minimization problem via equivalent factorized column-sparse regularized models. Math. Program. (2024). https://doi.org/10.1007/s10107-024-02103-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10107-024-02103-1
Keywords
- Low-rank matrix recovery
- Column-sparse regularization
- Nonconvex relaxation
- Strong stationary point
- Convergence analysis