Quantization for Low-Rank Matrix Recovery

We study Sigma-Delta quantization methods coupled with appropriate reconstruction algorithms for digitizing randomly sampled low-rank matrices. We show that the reconstruction error associated with our methods decays polynomially with the oversampling factor, and we leverage our results to obtain root-exponential accuracy by optimizing over the choice of quantization scheme. Additionally, we show that a random encoding scheme, applied to the quantized measurements, yields a near-optimal exponential bit-rate. As an added benefit, our schemes are robust both to noise and to deviations from the low-rank assumption. In short, we provide a full generalization of analogous results, obtained in the classical setup of bandlimited function acquisition, and more recently, in the finite frame and compressed sensing setups to the case of low-rank matrices sampled with sub-Gaussian linear operators. Finally, we believe our techniques for generalizing results from the compressed sensing setup to the analogous low-rank matrix setup is applicable to other quantization schemes.

[1]  Rongrong Wang,et al.  From Compressed Sensing to Compressed Bit-Streams: Practical Encoders, Tractable Decoders , 2016, IEEE Transactions on Information Theory.

[2]  Rayan Saab,et al.  Sigma-Delta quantization of sub-Gaussian frame expansions and its application to compressed sensing , 2013, ArXiv.

[3]  Emmanuel J. Candès,et al.  Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements , 2011, IEEE Transactions on Information Theory.

[4]  Stephen Becker,et al.  Quantum state tomography via compressed sensing. , 2009, Physical review letters.

[5]  Adel Javanmard,et al.  1-bit matrix completion under exact low-rank constraint , 2015, 2015 49th Annual Conference on Information Sciences and Systems (CISS).

[6]  Pablo A. Parrilo,et al.  Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..

[7]  Laurent Jacques,et al.  Quantization and Compressive Sensing , 2014, ArXiv.

[8]  Rayan Saab,et al.  Quantized compressed sensing for partial random circulant matrices , 2017, 2017 International Conference on Sampling Theory and Applications (SampTA).

[9]  I. Daubechies,et al.  Approximating a bandlimited function using very coarsely quantized data: A family of stable sigma-delta modulators of arbitrary order , 2003 .

[10]  Roman Vershynin,et al.  Introduction to the non-asymptotic analysis of random matrices , 2010, Compressed Sensing.

[11]  Qiang Yang,et al.  One-Class Collaborative Filtering , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[12]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[13]  M. Talagrand.  The Generic Chaining , 2005 .

[14]  慧 廣瀬.  A Mathematical Introduction to Compressive Sensing , 2015 .

[15]  Andrea Montanari,et al.  Matrix Completion from Noisy Entries , 2009, J. Mach. Learn. Res..

[16]  Rongrong Wang,et al.  Quantization of compressive samples with stable and robust recovery , 2015, ArXiv.

[17]  Hiroshi Inose,et al.  A unity bit coding method by negative feedback , 1963 .

[18]  G. Sapiro,et al.  A collaborative framework for 3D alignment and classification of heterogeneous subvolumes in cryo-electron tomography. , 2013, Journal of structural biology.

[19]  Ewout van den Berg,et al.  1-Bit Matrix Completion , 2012, ArXiv.

[20]  Babak Hassibi,et al.  A simplified approach to recovery conditions for low rank matrices , 2011, 2011 IEEE International Symposium on Information Theory Proceedings.

[21]  Rayan Saab,et al.  Near-Optimal Encoding for Sigma-Delta Quantization of Finite Frame Expansions , 2013, ArXiv.

[22]  Rayan Saab,et al.  Sigma delta quantization for compressed sensing , 2010, 2010 44th Annual Conference on Information Sciences and Systems (CISS).

[23]  Richard G. Baraniuk,et al.  Matrix recovery from quantized and corrupted measurements , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  Yin Zhang,et al.  Exploiting temporal stability and low-rank structure for localization in mobile networks , 2010, MobiCom.

[25]  Emmanuel J. Candès,et al.  The Power of Convex Relaxation: Near-Optimal Matrix Completion , 2009, IEEE Transactions on Information Theory.

[26]  Felix Krahmer,et al.  An optimal family of exponentially accurate one‐bit Sigma‐Delta quantization schemes , 2010, ArXiv.

[27]  Wen-Xin Zhou,et al.  A max-norm constrained minimization approach to 1-bit matrix completion , 2013, J. Mach. Learn. Res..

[28]  Yi Ma,et al.  The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices , 2010, Journal of structural biology.

[29]  Rayan Saab,et al.  Root-Exponential Accuracy for Coarse Quantization of Finite Frame Expansions , 2012, IEEE Transactions on Information Theory.

[30]  John J. Benedetto,et al.  Sigma-delta quantization and finite frames , 2004, ICASSP.

[31]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

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

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

[34]  Holger Rauhut,et al.  Suprema of Chaos Processes and the Restricted Isometry Property , 2012, ArXiv.

[35]  Eric Moulines,et al.  Probabilistic low-rank matrix completion on finite alphabets , 2014, NIPS.

[36]  C. S. Güntürk.  One‐bit sigma‐delta quantization with exponential accuracy , 2003 .

[37]  R. Dudley.  The Sizes of Compact Subsets of Hilbert Space and Continuity of Gaussian Processes , 1967 .