Robust Low-Tubal-Rank Tensor Completion via Convex Optimization

This paper considers the problem of recovering multidimensional array, in particular third-order tensor, from a random subset of its arbitrarily corrupted entries. Our study is based on a recently proposed algebraic framework in which the tensorSVD is introduced to capture the low-tubal-rank structure in tensor. We analyze the performance of a convex program, which minimizes a weighted combination of the tensor nuclear norm, a convex surrogate for the tensor tubal rank, and the tensor `1 norm. We prove that under certain incoherence conditions, this program can recover the tensor exactly with overwhelming probability, provided that its tubal rank is not too large and that the corruptions are reasonably sparse. The number of required observations is order optimal (up to a logarithm factor) when comparing with the degrees of freedom of the low-tubal-rank tensor. Numerical experiments verify our theoretical results and realworld applications demonstrate the effectiveness of our algorithm.

[1]  Hong Cheng,et al.  Robust Principal Component Analysis with Missing Data , 2014, CIKM.

[2]  Karen S. Braman Third-Order Tensors as Linear Operators on a Space of Matrices , 2010 .

[3]  Hisashi Kashima,et al.  Statistical Performance of Convex Tensor Decomposition , 2011, NIPS.

[4]  Journal of the Optical Society of America , 1950, Nature.

[5]  Wei Liu,et al.  Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Bo Huang,et al.  Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery , 2013, ICML.

[7]  Wei Liu,et al.  Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Arieh Iserles,et al.  On the Foundations of Computational Mathematics , 2001 .

[9]  Ryota Tomioka,et al.  Estimation of low-rank tensors via convex optimization , 2010, 1010.0789.

[10]  Lars Karlsson,et al.  Parallel algorithms for tensor completion in the CP format , 2016, Parallel Comput..

[11]  Karen O. Egiazarian,et al.  Image restoration by sparse 3D transform-domain collaborative filtering , 2008, Electronic Imaging.

[12]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[13]  J. Coyle Inverse Problems , 2004 .

[14]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[15]  Misha Elena Kilmer,et al.  Third-Order Tensors as Operators on Matrices: A Theoretical and Computational Framework with Applications in Imaging , 2013, SIAM J. Matrix Anal. Appl..

[16]  Anil C. Kokaram,et al.  On missing data treatment for degraded video and film archives: a survey and a new Bayesian approach , 2004, IEEE Transactions on Image Processing.

[17]  B. Recht,et al.  Tensor completion and low-n-rank tensor recovery via convex optimization , 2011 .

[18]  Parikshit Shah,et al.  Sparse and Low-Rank Tensor Decomposition , 2015, NIPS.

[19]  Xiaodong Li,et al.  Compressed Sensing and Matrix Completion with Constant Proportion of Corruptions , 2011, Constructive Approximation.

[20]  Jiawei Han,et al.  Robust Tensor Decomposition with Gross Corruption , 2014, NIPS.

[21]  Jieping Ye,et al.  Tensor Completion for Estimating Missing Values in Visual Data , 2013, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  George G. Lorentz,et al.  Constructive Approximation , 1993, Grundlehren der mathematischen Wissenschaften.

[23]  A N Rajagopalan,et al.  Recursive framework for joint inpainting and de-noising of photographic films. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[24]  M. Kilmer,et al.  Factorization strategies for third-order tensors , 2011 .