Abstract
The matrix nuclear norm has been widely applied to approximate the matrix rank for low-rank tensor completion because of its convexity. However, this relaxation may make the solution seriously deviate from the original solution for real-world data recovery. In this paper, using a nonconvex approximation of rank, i.e., the Schatten-p norm, we propose a novel model for tensor completion. It’s hard to solve this model directly because the objective function of the model is nonconvex. To solve the model, we develop a variant of this model via the classical quadric penalty method, and propose an algorithm, i.e., SpBCD, based on the block coordinate descent method. Although the objective function of the variant is nonconvex, we show that the sequence generated by SpBCD is convergent to a critical point. Our numerical experiments on real-world data show that SpBCD delivers state-of-art performance in recovering missing data.
Similar content being viewed by others
References
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of ACM Siggraph, pp. 414–424, New Orleans, USA (2000)
Komodakis, N., Tziritas, G.: Image completion using global optimization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 417–424 (2006)
Korah, T., Rasmussen, C.: Spatio-temporal impainting for recovering texture maps of occluded building facades. IEEE Trans. Image Process. 16(7), 2262–2271 (2007)
Patwardhan, K.A., Spiro, G., Bertalmio, M.: Video inpainting under constrained camera motion. IEEE Trans. Image Process. 16(2), 545–553 (2007)
Varghees, V.N., Manikandan, M.S., Gini, R.: Adaptive MRI image denoising using total-variation and local noise estimation. In: Processing of the 2012 International Conference on Advances in Engineering, Science and Management (ICAESM), pp. 506–511 (2012)
Li, N., Li, B.: Tensor completion for on-board compression of hyperspectral images. In: IEEE International Conference on Image Processing, pp. 517–520 (2015)
Xing, Z., Zhou, M., Castrodad, A., Saprio, G., Carin, L.: Dictionary learning for noisy and incomplete hyperspectral images. SIAM J. Imaging Sci. 5(1), 33–56 (2012)
Liu, Y., Jiao, L., Shang, F.: An efficient matrix factorization method for tensor completion. IEEE Signal Process. Lett. 20(4), 307–310 (2013)
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)
Nie, F., Wang, H., Cai, X., Huang, H., Ding, C.: Robust matrix completion via joint schatten-p norm and $ L_p $ norm minimization. In: ICDM, pp. 566–574 (2012)
Cai, T.T., Zhou, W.: Matrix completion via max-norm constrained optimization. Electron. J. Stat. 10(1), 1493–1525 (2016)
Koltchinskii, Vladimir: Von neumann entropy penalization and low-rank matrix estimation. Ann. Stat. 39(6), 2936–2973 (2011)
Ma, S., Goldfarb, D., Chen, L.: Fixed point and bregman iterative methods for matrix rank minimization. Math. Program. 128(1–2), 321–353 (2011)
Toh, K.C., Tun, S.: An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems. Pac. J. Optim. 6(3), 615–640 (2010)
Wen, Z., Yin, W., Zhang, Y.: Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm. Math. Program. Comput. 4(4), 1–29 (2012)
Chen, C., He, B., Yuan, X.: Matrix completion via an alternating direction method. IMA J. Numer. Anal. 32(1), 227–245 (2012)
Xu, Y., Yin, W., Wen, Z., Zhang, Y.: An alternating direction algorithm for matrix completion with nonnegative factors. J. Front. Math. China 7(2), 365–384 (2011)
Tucker, L.R.: Implications of factor analysis of three-way matrices for measurement of change. In: Harris, C.W. (ed.) Problems in Measuring Change, pp. 122–137. University of Wisconsin Press, Madison (1963)
Tucker, L.R.: Some mathematical notes on three-mode factor analysis. Psychometrika 31(3), 279–311 (1966)
Hackbusch, W., Küuhn, S.: A new scheme for the tensor representation. J. Fourier Anal. Appl. 15(5), 706–722 (2009)
Grasedyck, L.: Hierarchical singular value decomposition of tensors. SIAM J. Matrix Anal. Appl. 31(4), 2029–2054 (2010)
Oseledets, I.V., Tyrtyshnikov, E.E.: Breaking the curse of dimensionality, or how to use SVD in many dimensions. SIAM J. Sci. Comput. 31(5), 3744–3759 (2009)
Oseledets, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33(5), 2295–2317 (2011)
Kruskal, J.B.: Rank decomposition and uniqueness for 3-way and N-way arrays. In: Multiway Data Analysis, pp. 7–18 (1988)
Liu, J., Musialski, P., Wonka, P., Ye, J.P.: Tensor completion for estimating missing values in visual data. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 1126–1153 (2013)
Kolda, G., Bader, W.: Tensor decomposition and application. SIAM Rev. 51(3), 455–500 (2009)
Kressner, D., Steinlechner, M., Vandereycken, B.: Low-rank tensor completion by Riemannian optimization. BIT Numer. Math. 54(2), 447–468 (2014)
Xu, Y., Hao, R., Yin, W., Su, Z.: Parallel matrix factorization for low-rank tensor completion. Inverse Probl. Imaging 9(2), 601–624 (2015)
Gao, S., Fan, Q.: A mixture of nuclear norm and matrix factorization for tensor completion. J. Sci. Comput. 75(1), 43–64 (2018)
Sun, W., Yuan, Y.: Optimization Theory and Methods: Nonlinear Programming. Springer, New York (2006)
Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2009)
Wen, Z., Yin, W., Zhang, Y.: Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm. Math. Program. Comput. 4(4), 333–361 (2012)
Nesterov, Y.: Smooth minimization of non-smooth function. Math. Program. 20(6), 127–152 (2005)
Cai, J., Candès, F.J., Shen, Z.: A singular value thresholding decomposition. UCLA CAM Report (2010)
Gandy, S., Recht, B., Yamada, I.: Tensor completion and low-n-rank tensor recovery via convex optimization. Inverse Probl. 27(2), 025010 (2011)
Tseng, P., Mangasarian, O.L.: Convergence of a block coordinate descent method for nondifferential minimization. J. Optim. Theory Appl. 109(3), 475–494 (2011)
Xu, Z., Chang, X., Xu, F., Zhang, H.: $ L_{1/2} $ regularization: a thresholding representation theory and a fast solver. IEEE Trans. Neur. Netw. Learn. Syst. 23(7), 1013–1027 (2012)
Łojasiewicz, S.: Une propriété topologique des sous-ensembles analytiques réels. Les Équations aux Dérivées Partielles 117, 87–89 (1963)
Kurdyka, K.: On gradients of functions definable in o-minimal structures. Ann. Inst. Fourier 48(3), 769–783 (1998)
Bertsekas, D.P.: Nonlinear Programming, 2nd edn, pp. 208–211. Athena Scientific, Nashua (1999)
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)
Yunus, A., Coskun, K., Akbar, A., Ismail, K., Fatemeh, K.: Uniform-geometric distribution. J. Stat. Comput. Simul. 86(9), 1754–1770 (2016)
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.
This research was supported by the National Science Foundation of China under Grant 61179039.
Rights and permissions
About this article
Cite this article
Gao, S., Fan, Q. Robust Schatten-p Norm Based Approach for Tensor Completion. J Sci Comput 82, 11 (2020). https://doi.org/10.1007/s10915-019-01108-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10915-019-01108-9