Exact Recovery of Tensor Robust Principal Component Analysis under Linear Transforms

This work studies the Tensor Robust Principal Component Analysis (TRPCA) problem, which aims to exactly recover the low-rank and sparse components from their sum. Our model is motivated by the recently proposed linear transforms based tensor-tensor product and tensor SVD. We define a new transforms depended tensor rank and the corresponding tensor nuclear norm. Then we solve the TRPCA problem by convex optimization whose objective is a weighted combination of the new tensor nuclear norm and the $\ell_1$-norm. In theory, we show that under certain incoherence conditions, the convex program exactly recovers the underlying low-rank and sparse components. It is of great interest that our new TRPCA model generalizes existing works. In particular, if the studied tensor reduces to a matrix, our TRPCA model reduces to the known matrix RPCA. Our new TRPCA which is allowed to use general linear transforms can be regarded as an extension of our former TRPCA work which uses the discrete Fourier transform. But their proof of the recovery guarantee is different. Numerical experiments verify our results and the application on image recovery demonstrates the superiority of our method.

[1]  David F. Gleich,et al.  The power and Arnoldi methods in an algebra of circulants , 2011, Numer. Linear Algebra Appl..

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

[3]  Zemin Zhang,et al.  Exact Tensor Completion Using t-SVD , 2015, IEEE Transactions on Signal Processing.

[4]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[5]  Christopher J. Hillar,et al.  Most Tensor Problems Are NP-Hard , 2009, JACM.

[6]  Massimiliano Pontil,et al.  A New Convex Relaxation for Tensor Completion , 2013, NIPS.

[7]  Shuicheng Yan,et al.  Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements , 2018, IJCAI.

[8]  M. Kilmer,et al.  Tensor-Tensor Products with Invertible Linear Transforms , 2015 .

[9]  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).

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

[11]  Johan A. K. Suykens,et al.  Tensor Versus Matrix Completion: A Comparison With Application to Spectral Data , 2011, IEEE Signal Processing Letters.

[12]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2009, Found. Comput. Math..

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

[14]  John Wright,et al.  Provable Models for Robust Low-Rank Tensor Completion , 2015 .

[15]  Nikos D. Sidiropoulos,et al.  Parallel factor analysis in sensor array processing , 2000, IEEE Trans. Signal Process..

[16]  Tamara G. Kolda,et al.  Scalable Tensor Factorizations with Missing Data , 2010, SDM.

[17]  Yudong Chen,et al.  Incoherence-Optimal Matrix Completion , 2013, IEEE Transactions on Information Theory.

[18]  Shuicheng Yan,et al.  A Unified Alternating Direction Method of Multipliers by Majorization Minimization , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Misha Elena Kilmer,et al.  Novel Methods for Multilinear Data Completion and De-noising Based on Tensor-SVD , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Steffen Staab,et al.  TripleRank: Ranking Semantic Web Data by Tensor Decomposition , 2009, SEMWEB.

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

[22]  Eric L. Miller,et al.  Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography , 2013, IEEE Transactions on Image Processing.

[23]  Demetri Terzopoulos,et al.  Multilinear Analysis of Image Ensembles: TensorFaces , 2002, ECCV.

[24]  Carla D. Martin,et al.  An Order-p Tensor Factorization with Applications in Imaging , 2013, SIAM J. Sci. Comput..

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

[26]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[27]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

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

[29]  Nadia Kreimer,et al.  Nuclear norm minimization and tensor completion in exploration seismology , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

[31]  S. Engelen,et al.  A fully robust PARAFAC method for analyzing fluorescence data , 2009 .

[32]  John Wright,et al.  RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Zuowei Shen,et al.  Robust Video Restoration by Joint Sparse and Low Rank Matrix Approximation , 2011, SIAM J. Imaging Sci..