Abstract
As we know, nuclear norm based regularization methods have the real-world applications in pattern recognition and computer vision. However, there exists a biased estimator when nuclear norm relaxes the rank function. To solve this issue, we focus on studying nonconvex rank regularization problems for both robust matrix completion (RMC) and low rank representation (LRR), respectively. By extending both to a general low rank matrix minimization problem, we develop a nonconvex alternating direction method of multipliers (ADMM). Moreover, the convergence results, i.e., the variable sequence generated by the nonconvex ADMM is bounded and its subsequence converges to a stationary point. Meanwhile, its limiting point satisfies the Karush-Kuhn-Tucher (KKT) conditions provided under some milder assumptions. Numerical experiments can verify the convergence properties of the theoretical results and the performance shows its superiority on both image inpainting and subspace clustering.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For \(\ell _p\)-norm, if \(\sigma _i=0\), then \(\partial f_{\lambda }(\sigma _i)=\{+\infty \}\), we can guarantee from the iteration rules for \(\mathbf {X}_{k+1}\) in subproblem (8) that the rank of the generated sequence \(\{\mathbf {X}_{k+1}\}\) is nonincreasing.
- 2.
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. 137(1–2), 91–129 (2013)
Bolte, J., Daniilidis, A., Lewis, A.: The Łojasiewicz inequality for nonsmooth subanalytic functions with applications to subgradient dynamical systems. SIAM. J. Optim. 17(4), 1205–1223 (2007)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146(1-2), 459–494 (2014)
Brbić, M., Kopriva, I.: \(\ell _0\)-motivated low-rank sparse subspace clustering. IEEE Trans. Cybern. 50(4), 1711–1725 (2020)
Candes, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3), 1–37 (2011)
Candes, E., Tao, T.: The power of convex relaxation: near-optimal matrix completion. IEEE Trans. Infor. Theo. 56(5), 2053–2080 (2010)
Chen, C., He, B., Ye, Y., Yuan, X.: The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent. Math. Program. 155(1–2), 57–79 (2016)
Chen, Y., Jalali, A., Sanghavi, S., Caramanis, C.: Low-rank matrix recovery from errors and erasures. IEEE Trans. Infor. Theo. 59(7), 4324–4337 (2013)
Clarke, F.: Optimization and nonsmooth analysis. Society for Industrial and Applied Mathematics (1990)
Dong, W., Wu, X.: Robust low rank subspace segmentation via joint \(\ell _{21} \)-norm minimization. Neural Process. Lett. 48(1), 299–312 (2018)
Friedman, J.H.: Fast sparse regression and classification. Int. J. Forecasting 28(3), 722–738 (2012)
Gao, C., Wang, N., Yu, Q., Zhang, Z.: A feasible nonconvex relaxation approach to feature selection. In: Proceedings Association Advancement Artificial Intelligence (AAAI), pp. 356–361 (2011)
Geman, D., Yang, C.: Nonlinear image recovery with half-quadratic regularization. IEEE Trans. Image. Process. 4(7), 932–946 (1994)
Gu, S., Xie, Q., Meng, D., Zuo, W., Feng, X., Zhang, L.: Weighted nuclear norm minimization and its applications to low level vision. Int. J. Comput. Vis. 121(2), 183–208 (2017)
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)
Hu, Z., Nie, F., Tian, L., Li, X.: A comprehensive survey for low rank regularization. arXiv preprint arXiv:1808.04521 (2018)
Kang, Z., Peng, C., Cheng, Q.: Robust subspace clustering via tighter rank approximation. In: Proceedings ACM Conference Information and Knowledge Management (CIKM), pp. 655–661 (2012)
Lan, X., Zhang, S., Yuen, P.C., Chellappa, R.: Learning common and feature-specific patterns: a novel multiple-sparse-representation-based tracker. IEEE Trans. Image. Process. 27(4), 2022–2037 (2018)
Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., Ma, Y.: Robust recovery of subspace structures by low-rank representation. IEEE Trans. Pattern. Anal. Mach. Intell. 35(1), 171–184 (2013)
Lu, C., Lin, Z., Yan, S.: Smoothed low rank and sparse matrix recovery by iteratively reweighted least squares minimization. IEEE Trans. Image. Process. 24(2), 646–654 (2015)
Lu, C., Tang, J., Yan, S., Lin, Z.: Nonconvex nonsmooth low-rank minimization via iteratively reweighted nuclear norm. IEEE Trans. Image. Process. 25(2), 829–839 (2016)
Lu, C., Zhu, C., Xu, C., Yan, S., Lin, Z.: Generalized singular value thresholding. In: Proceedings Association Advances Artificial Intelligence (AAAI), pp. 1805–1811 (2015)
Nie, F., Wang, H., Huang, H., Ding, C.: Joint Schatten-\(p\) norm and \(\ell _p\)-norm robust matrix completion for missing value recovery. Knowl. Infor. Syst. 42(3), 525–544 (2015)
Oh, T.H., Tai, Y., Bazin, J.C., Kim, H., Kweon, I.S.: Partial sum minimization of singular values in robust PCA: algorithm and applications. IEEE Trans. Pattern. Anal. Mach. Intell. 38(4), 744–758 (2015)
Trzasko, J., Manduca, A.: Highly undersampled magnetic resonance image reconstruction via homotopic \(\ell _p\)-minimization. IEEE Trans. Med. Image. 28(1), 106–121 (2009)
Wang, Y., Yin, W., Zeng, J.: Global convergence of ADMM in nonconvex nonsmooth optimization. J. Sci. Comput. 78(1), 29–63 (2019)
Wei, L., Wang, X., Wu, A., Zhou, R., Zhu, C.: Robust subspace segmentation by self-representation constrained low-rank representation. Neural. Process. Lett. 48(3), 1671–1691 (2018)
Wen, F., Chu, L., Liu, P., Qiu, R.C.: A survey on nonconvex regularization-based sparse and low-rank recovery in signal processing, statistics, and machine learning. IEEE Access. 6, 69883–69906 (2018)
Xie, Y., Gu, S., Liu, Y., Zuo, W., Zhang, W., Zhang, L.: Weighted Schatten-\(p\) norm minimization for image denoising and background subtraction. IEEE Trans. Image. Process. 25(10), 4842–4857 (2016)
Yang, L., Pong, T., Chen, X.: Alternating direction method of multipliers for nonconvex background/foreground extraction. SIAM J. Imag. Sci. 10(1), 74–110 (2017)
Yao, Q., Kwok, J.T., Gao, F., Chen, W., Liu, T.: Efficient inexact proximal gradient algorithm for nonconvex problems. In: Proceedings Association Advancement Artificial Intelligence (AAAI), pp. 3308–3314 (2017)
Zhang, H., Gong, C., Qian, J., Zhang, B., Xu, C., Yang, J.: Efficient recovery of low-rank matrix via double nonconvex nonsmooth rank minimization. IEEE Trans. Neural Netw. Learn. Syst. 30(10), 2916–2925 (2019)
Zhang, H., Qian, F., Shang, F., Du, W., Qian, J., Yang, J.: Global convergence guarantees of (A)GIST for a family of nonconvex sparse learning problems. IEEE Trans. Cybern. https://doi.org/10.1109/TCYB.2020.3010960 (2020)
Zhang, H., Qian, J., Gao, J., Yang, J., Xu, C.: Scalable proximal Jacobian iteration method with global convergence analysis for nonconvex unconstrained composite optimizations. IEEE Trans. Neural Netw. Learn. Syst. 30(9), 2825–2839 (2019)
Zhang, H., Yang, J., Qian, J., Luo, W.: Nonconvex relaxation based matrix regression for face recognition with structural noise and mixed noise. Neurocomput. 269(20), 188–198 (2017)
Zhang, H., Yang, J., Shang, F., Gong, C., Zhang, Z.: LRR for subspace segmentation via tractable Schatten-\(p\) norm minimization and factorization. IEEE Trans. Cybern. 49(5), 1722–1734 (2019)
Acknowledgements
The authors would like to thank the anonymous reviewers for their valuable comments. This work was supported in part by the National Natural Science Fund for Distinguished Young Scholars under Grant 61725301, in part by the National Science Fund of China under Grant 61973124, 61702197, 61876083, and 61906067, in part by the China Postdoctoral Science Foundation under Grant 2019M651415 and 2020T130191, and in part by the University of Macau under UM Macao Talent Programme (UMMTP-2020-01).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, H., Luo, W., Du, W., Qian, J., Yang, J., Zhang, B. (2021). Robust Recovery of Low Rank Matrix by Nonconvex Rank Regularization. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12889. Springer, Cham. https://doi.org/10.1007/978-3-030-87358-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-87358-5_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87357-8
Online ISBN: 978-3-030-87358-5
eBook Packages: Computer ScienceComputer Science (R0)