Universality in Learning from Linear Measurements

We study the problem of recovering a structured signal from independently and identically drawn linear measurements. A convex penalty function $f(\cdot)$ is considered which penalizes deviations from the desired structure, and signal recovery is performed by minimizing $f(\cdot)$ subject to the linear measurement constraints. The main question of interest is to determine the minimum number of measurements that is necessary and sufficient for the perfect recovery of the unknown signal with high probability. Our main result states that, under some mild conditions on $f(\cdot)$ and on the distribution from which the linear measurements are drawn, the minimum number of measurements required for perfect recovery depends only on the first and second order statistics of the measurement vectors. As a result, the required of number of measurements can be determining by studying measurement vectors that are Gaussian (and have the same mean vector and covariance matrix) for which a rich literature and comprehensive theory exists. As an application, we show that the minimum number of random quadratic measurements (also known as rank-one projections) required to recover a low rank positive semi-definite matrix is $3nr$, where $n$ is the dimension of the matrix and $r$ is its rank. As a consequence, we settle the long standing open question of determining the minimum number of measurements required for perfect signal recovery in phase retrieval using the celebrated PhaseLift algorithm, and show it to be $3n$.

[1]  Babak Hassibi,et al.  A Universal Analysis of Large-Scale Regularized Least Squares Solutions , 2017, NIPS.

[2]  M. Stojnic Upper-bounding $\ell_1$-optimization weak thresholds , 2013 .

[3]  Joel A. Tropp,et al.  Universality laws for randomized dimension reduction, with applications , 2015, ArXiv.

[4]  Andrea J. Goldsmith,et al.  Estimation of simultaneously structured covariance matrices from quadratic measurements , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Geert Leus,et al.  Compressive Wideband Power Spectrum Estimation , 2012, IEEE Transactions on Signal Processing.

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

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

[8]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[9]  Pablo A. Parrilo,et al.  The Convex Geometry of Linear Inverse Problems , 2010, Foundations of Computational Mathematics.

[10]  Andrea Montanari,et al.  Message-passing algorithms for compressed sensing , 2009, Proceedings of the National Academy of Sciences.

[11]  Joel A. Tropp,et al.  Living on the edge: phase transitions in convex programs with random data , 2013, 1303.6672.

[12]  Yonina C. Eldar,et al.  Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices , 2012, IEEE Transactions on Information Theory.

[13]  Joel A. Tropp,et al.  An Introduction to Matrix Concentration Inequalities , 2015, Found. Trends Mach. Learn..

[14]  Mihailo Stojnic,et al.  Strong thresholds for ℓ2/ℓ1-optimization in block-sparse compressed sensing , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  Sujay Sanghavi,et al.  The Local Convexity of Solving Systems of Quadratic Equations , 2015, 1506.07868.

[16]  Christos Thrampoulidis,et al.  Precise Error Analysis of Regularized $M$ -Estimators in High Dimensions , 2016, IEEE Transactions on Information Theory.

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

[18]  Noureddine El Karoui,et al.  Operator norm consistent estimation of large-dimensional sparse covariance matrices , 2008, 0901.3220.

[19]  A. Willsky,et al.  Latent variable graphical model selection via convex optimization , 2010 .

[20]  Yonina C. Eldar,et al.  GESPAR: Efficient Phase Retrieval of Sparse Signals , 2013, IEEE Transactions on Signal Processing.

[21]  M. Rudelson,et al.  Sparse reconstruction by convex relaxation: Fourier and Gaussian measurements , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

[22]  E. Candès The restricted isometry property and its implications for compressed sensing , 2008 .

[23]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

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

[25]  Christos Thrampoulidis,et al.  Regularized Linear Regression: A Precise Analysis of the Estimation Error , 2015, COLT.

[26]  Yue Sun,et al.  Low-Rank Positive Semidefinite Matrix Recovery From Corrupted Rank-One Measurements , 2016, IEEE Transactions on Signal Processing.

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

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

[29]  Y. Gordon Some inequalities for Gaussian processes and applications , 1985 .

[30]  David L. Donoho,et al.  Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[31]  Justin K. Romberg,et al.  Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals , 2009, IEEE Transactions on Information Theory.

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

[33]  Anru Zhang,et al.  ROP: Matrix Recovery via Rank-One Projections , 2013, ArXiv.

[34]  Y. Gordon On Milman's inequality and random subspaces which escape through a mesh in ℝ n , 1988 .

[35]  Babak Hassibi,et al.  New Null Space Results and Recovery Thresholds for Matrix Rank Minimization , 2010, ArXiv.