Phase Retrieval of Low-Rank Matrices by Anchored Regression

We study the low-rank phase retrieval problem, where we try to recover a $d_1\times d_2$ low-rank matrix from a series of phaseless linear measurements. This is a fourth-order inverse problem, as we are trying to recover factors of matrix that have been put through a quadratic nonlinearity after being multiplied together. We propose a solution to this problem using the recently introduced technique of anchored regression. This approach uses two different types of convex relaxations: we replace the quadratic equality constraints for the phaseless measurements by a search over a polytope, and enforce the rank constraint through nuclear norm regularization. The result is a convex program that works in the space of $d_1 \times d_2$ matrices. We analyze two specific scenarios. In the first, the target matrix is rank-$1$, and the observations are structured to correspond to a phaseless blind deconvolution. In the second, the target matrix has general rank, and we observe the magnitudes of the inner products against a series of independent Gaussian random matrices. In each of these problems, we show that the anchored regression returns an accurate estimate from a near-optimal number of measurements given that we have access to an anchor matrix of sufficient quality. We also show how to create such an anchor in the phaseless blind deconvolution problem, again from an optimal number of measurements, and present a partial result in this direction for the general rank problem.

[1]  V. Koltchinskii,et al.  Nuclear norm penalization and optimal rates for noisy low rank matrix completion , 2010, 1011.6256.

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

[3]  Justin Romberg,et al.  Multichannel myopic deconvolution in underwater acoustic channels via low-rank recovery. , 2017, The Journal of the Acoustical Society of America.

[4]  Yonina C. Eldar,et al.  Blind Phaseless Short-Time Fourier Transform Recovery , 2018, IEEE Transactions on Information Theory.

[5]  Andrea J. Goldsmith,et al.  Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming , 2013, IEEE Transactions on Information Theory.

[6]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.

[7]  Justin K. Romberg,et al.  Compressed Subspace Matching on the Continuum , 2014, ArXiv.

[8]  Emmanuel J. Candès,et al.  Templates for convex cone problems with applications to sparse signal recovery , 2010, Math. Program. Comput..

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

[10]  Justin K. Romberg,et al.  Compressive Multiplexing of Correlated Signals , 2013, IEEE Transactions on Information Theory.

[11]  Andrea Montanari,et al.  Matrix completion from a few entries , 2009, 2009 IEEE International Symposium on Information Theory.

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

[13]  Donald C. Cox,et al.  Robust frequency and timing synchronization for OFDM , 1997, IEEE Trans. Commun..

[14]  Felix Krahmer,et al.  Spectral Methods for Passive Imaging: Non-asymptotic Performance and Robustness , 2017, SIAM J. Imaging Sci..

[15]  Chandler Davis The rotation of eigenvectors by a perturbation , 1963 .

[16]  Tom Goldstein,et al.  Convex Phase Retrieval without Lifting via PhaseMax , 2017, ICML.

[17]  Rafa l Lata la Estimates of moments and tails of Gaussian chaoses , 2005 .

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

[19]  Xiaodong Li,et al.  Sparse Signal Recovery from Quadratic Measurements via Convex Programming , 2012, SIAM J. Math. Anal..

[20]  Laurent Demanet,et al.  Leveraging Diversity and Sparsity in Blind Deconvolution , 2016, IEEE Transactions on Information Theory.

[21]  Justin Romberg,et al.  Fast and Guaranteed Blind Multichannel Deconvolution Under a Bilinear System Model , 2016, IEEE Transactions on Information Theory.

[22]  Yanjun Li,et al.  Blind Recovery of Sparse Signals From Subsampled Convolution , 2015, IEEE Transactions on Information Theory.

[23]  Augustin Cosse,et al.  A note on the blind deconvolution of multiple sparse signals from unknown subspaces , 2017, Optical Engineering + Applications.

[24]  Sjoerd Dirksen,et al.  Dimensionality Reduction with Subgaussian Matrices: A Unified Theory , 2014, Foundations of Computational Mathematics.

[25]  Xiaodong Li,et al.  Phase Retrieval via Wirtinger Flow: Theory and Algorithms , 2014, IEEE Transactions on Information Theory.

[26]  Holger Rauhut,et al.  A Mathematical Introduction to Compressive Sensing , 2013, Applied and Numerical Harmonic Analysis.

[27]  Prateek Jain,et al.  Phase Retrieval Using Alternating Minimization , 2013, IEEE Transactions on Signal Processing.

[28]  Justin Romberg,et al.  Phase Retrieval Meets Statistical Learning Theory: A Flexible Convex Relaxation , 2016, AISTATS.

[29]  Yuejie Chi,et al.  Guaranteed Blind Sparse Spikes Deconvolution via Lifting and Convex Optimization , 2015, IEEE Journal of Selected Topics in Signal Processing.

[30]  Thomas Strohmer,et al.  Self-Calibration via Linear Least Squares , 2016, ArXiv.

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

[32]  Iosif Pinelis,et al.  Some Inequalities for the Distribution of Sums of Independent Random Variables , 1978 .

[33]  Justin Romberg,et al.  Solving Equations of Random Convex Functions via Anchored Regression , 2017, Found. Comput. Math..

[34]  M. Junge,et al.  Noncommutative Bennett and Rosenthal inequalities , 2011, 1111.1027.

[35]  Wen Huang,et al.  Blind Deconvolution by a Steepest Descent Algorithm on a Quotient Manifold , 2017, SIAM J. Imaging Sci..

[36]  R. Latala Estimates of moments and tails of Gaussian chaoses , 2005, math/0505313.

[37]  Yuxin Chen,et al.  Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems , 2015, NIPS.

[38]  R Bouziane,et al.  Blind symbol synchronization for direct detection optical OFDM using a reduced number of virtual subcarriers. , 2015, Optics express.

[39]  Yonina C. Eldar,et al.  Phase Retrieval: An Overview of Recent Developments , 2015, ArXiv.

[40]  Emmanuel J. Candès,et al.  PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming , 2011, ArXiv.

[41]  Yan Shuo Tan,et al.  Phase Retrieval via Randomized Kaczmarz: Theoretical Guarantees , 2017, ArXiv.

[42]  Yonina C. Eldar,et al.  Low-Rank Phase Retrieval , 2016, IEEE Transactions on Signal Processing.

[43]  Joel A. Tropp,et al.  User-Friendly Tail Bounds for Sums of Random Matrices , 2010, Found. Comput. Math..

[44]  Justin Romberg,et al.  Round-robin multiple-source localization. , 2014, The Journal of the Acoustical Society of America.

[45]  Xiaodong Li,et al.  Rapid, Robust, and Reliable Blind Deconvolution via Nonconvex Optimization , 2016, Applied and Computational Harmonic Analysis.

[46]  Thomas Strohmer,et al.  Self-Calibration and Bilinear Inverse Problems via Linear Least Squares , 2016, SIAM J. Imaging Sci..

[47]  Alexandre d'Aspremont,et al.  Phase recovery, MaxCut and complex semidefinite programming , 2012, Math. Program..

[48]  W. Kahan,et al.  The Rotation of Eigenvectors by a Perturbation. III , 1970 .

[49]  P. Wedin Perturbation bounds in connection with singular value decomposition , 1972 .

[50]  Laura Waller,et al.  Algorithmic Self-calibration of Illumination Angles in Fourier Ptychographic Microscopy , 2016 .

[51]  Justin K. Romberg,et al.  An Overview of Low-Rank Matrix Recovery From Incomplete Observations , 2016, IEEE Journal of Selected Topics in Signal Processing.

[52]  Xiaodong Li,et al.  Optimal Rates of Convergence for Noisy Sparse Phase Retrieval via Thresholded Wirtinger Flow , 2015, ArXiv.

[53]  Eric Moulines,et al.  Subspace methods for the blind identification of multichannel FIR filters , 1995, IEEE Trans. Signal Process..

[54]  Ali Ahmed,et al.  Blind Deconvolutional Phase Retrieval via Convex Programming , 2018, NeurIPS.

[55]  John Wright,et al.  A Geometric Analysis of Phase Retrieval , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

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

[57]  Babak Hassibi,et al.  Sparse Phase Retrieval: Uniqueness Guarantees and Recovery Algorithms , 2013, IEEE Transactions on Signal Processing.

[58]  Yonina C. Eldar,et al.  Solving Systems of Random Quadratic Equations via Truncated Amplitude Flow , 2016, IEEE Transactions on Information Theory.

[59]  Yanjun Li,et al.  Blind Gain and Phase Calibration via Sparse Spectral Methods , 2017, IEEE Transactions on Information Theory.

[60]  Liming Wang,et al.  Blind Deconvolution From Multiple Sparse Inputs , 2016, IEEE Signal Processing Letters.

[61]  T. Kailath,et al.  A least-squares approach to blind channel identification , 1995, IEEE Trans. Signal Process..

[62]  S. Mendelson,et al.  Minimax rate of convergence and the performance of empirical risk minimization in phase recovery , 2015 .

[63]  Xiaodong Li,et al.  Solving Quadratic Equations via PhaseLift When There Are About as Many Equations as Unknowns , 2012, Found. Comput. Math..

[64]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[65]  Zhihui Zhu,et al.  Super-Resolution of Complex Exponentials From Modulations With Unknown Waveforms , 2016, IEEE Transactions on Information Theory.

[66]  Joseph M Kahn,et al.  Direct-detection mode-division multiplexing in modal basis using phase retrieval. , 2016, Optics letters.

[67]  Xiaodong Li,et al.  Phase Retrieval from Coded Diffraction Patterns , 2013, 1310.3240.

[68]  Justin K. Romberg,et al.  Blind Deconvolution Using Convex Programming , 2012, IEEE Transactions on Information Theory.

[69]  Yonina C. Eldar,et al.  Sparse Phase Retrieval from Short-Time Fourier Measurements , 2014, IEEE Signal Processing Letters.