Provable Low-Rank Tensor Recovery

In this paper, we rigorously study tractable models for provably recovering low-rank tensors. Unlike their matrix-based predecessors, current convex approaches for recovering low-rank tensors based on incomplete (tensor completion) and/or grossly corrupted (tensor robust principal analysis) observations still suffer from the lack of theoretical guarantees, although they have been used in various recent applications and have exhibited promising empirical performance. In this work, we attempt to fill this gap. Specifically, we propose a class of convex recovery models (including strongly convex programs) that can be proved to guarantee exact recovery under certain conditions. All parameters in our formulations can be determined beforehand based on the measurement data and thus there is no parameter tuning involved.

[1]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[2]  J. Chang,et al.  Analysis of individual differences in multidimensional scaling via an n-way generalization of “Eckart-Young” decomposition , 1970 .

[3]  Richard A. Harshman,et al.  Foundations of the PARAFAC procedure: Models and conditions for an "explanatory" multi-model factor analysis , 1970 .

[4]  丸山 徹.  Convex Analysisの二,三の進展について , 1977 .

[5]  K. Plataniotis,et al.  Color Image Processing and Applications , 2000 .

[6]  Demetri Terzopoulos,et al.  Multilinear subspace analysis of image ensembles , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[7]  Huan Liu,et al.  CubeSVD: a novel approach to personalized Web search , 2005, WWW '05.

[8]  Yurii Nesterov,et al.  Smooth minimization of non-smooth functions , 2005, Math. Program..

[9]  Nima Mesgarani,et al.  Discrimination of speech from nonspeech based on multiscale spectro-temporal Modulations , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[10]  John Wright,et al.  Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization , 2009, NIPS.

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

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

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

[14]  John Wright,et al.  Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization , 2009, NIPS.

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

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

[17]  Baoxin Li,et al.  Tensor completion for on-board compression of hyperspectral images , 2010, 2010 IEEE International Conference on Image Processing.

[18]  Wotao Yin,et al.  Analysis and Generalizations of the Linearized Bregman Method , 2010, SIAM J. Imaging Sci..

[19]  Yin Li,et al.  Optimum Subspace Learning and Error Correction for Tensors , 2010, ECCV.

[20]  Nikos D. Sidiropoulos,et al.  Tensor Algebra and Multidimensional Harmonic Retrieval in Signal Processing for MIMO Radar , 2010, IEEE Transactions on Signal Processing.

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

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

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

[24]  J. Suykens,et al.  Nuclear Norms for Tensors and Their Use for Convex Multilinear Estimation , 2011 .

[25]  Hui Zhang,et al.  Strongly Convex Programming for Exact Matrix Completion and Robust Principal Component Analysis , 2011, ArXiv.

[26]  David Gross,et al.  Recovering Low-Rank Matrices From Few Coefficients in Any Basis , 2009, IEEE Transactions on Information Theory.

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

[28]  Pablo A. Parrilo,et al.  Rank-Sparsity Incoherence for Matrix Decomposition , 2009, SIAM J. Optim..

[29]  Benjamin Recht,et al.  A Simpler Approach to Matrix Completion , 2009, J. Mach. Learn. Res..

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

[31]  Shay B. Cohen,et al.  Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs , 2012, NIPS.

[32]  Qun Wan,et al.  Strongly Convex Programming for Principal Component Pursuit , 2012, ArXiv.

[33]  Shuchin Aeron,et al.  5D and 4D pre-stack seismic data completion using tensor nuclear norm (TNN) , 2013, SEG Technical Program Expanded Abstracts 2013.

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

[35]  Johan A. K. Suykens,et al.  Learning with tensors: a framework based on convex optimization and spectral regularization , 2014, Machine Learning.

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

[37]  Shiqian Ma,et al.  Accelerated Linearized Bregman Method , 2011, J. Sci. Comput..

[38]  J. Gondzio,et al.  A Second-Order Method for Strongly Convex L1-Regularization Problems , 2013 .

[39]  Xianjun Shi,et al.  A Fixed Point Iterative Method for Low $n$-Rank Tensor Pursuit , 2013, IEEE Transactions on Signal Processing.

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

[41]  Donald Goldfarb,et al.  Robust Low-Rank Tensor Recovery: Models and Algorithms , 2013, SIAM J. Matrix Anal. Appl..

[42]  Anima Anandkumar,et al.  Tensor decompositions for learning latent variable models , 2012, J. Mach. Learn. Res..

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

[44]  Shiqian Ma,et al.  Tensor principal component analysis via convex optimization , 2012, Math. Program..