Phase retrieval via linear programming: Fundamental limits and algorithmic improvements

A recently proposed convex formulation of the phase retrieval problem estimates the unknown signal by solving a simple linear program. This new scheme, known as PhaseMax, is computationally efficient compared to standard convex relaxation methods based on lifting techniques. In this paper, we present an exact performance analysis of PhaseMax under Gaussian measurements in the large system limit. In contrast to previously known performance bounds in the literature, our results are asymptotically exact and they also reveal a sharp phase transition phenomenon. Furthermore, the geometrical insights gained from our analysis led us to a novel nonconvex formulation of the phase retrieval problem and an accompanying iterative algorithm based on successive linearization and maximization over a polytope. This new algorithm, which we call PhaseLamp, has provably superior recovery performance over the original PhaseMax method.

[1]  Kenneth Lange,et al.  MM optimization algorithms , 2016 .

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

[3]  Yue M. Lu,et al.  Phase Transitions of Spectral Initialization for High-Dimensional Nonconvex Estimation , 2017, Information and Inference: A Journal of the IMA.

[4]  Mihailo Stojnic,et al.  A framework to characterize performance of LASSO algorithms , 2013, ArXiv.

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

[6]  R. Gerchberg.  A practical algorithm for the determination of phase from image and diffraction plane pictures , 1972 .

[7]  Richard G. Baraniuk,et al.  A Field Guide to Forward-Backward Splitting with a FASTA Implementation , 2014, ArXiv.

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

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

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

[11]  Yue M. Lu,et al.  Fundamental limits of phasemax for phase retrieval: A replica analysis , 2017, 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[12]  Vladislav Voroninski,et al.  An Elementary Proof of Convex Phase Retrieval in the Natural Parameter Space via the Linear Program PhaseMax , 2016, ArXiv.

[13]  R. Balan,et al.  Painless Reconstruction from Magnitudes of Frame Coefficients , 2009 .

[14]  Klaus J. Miescke,et al.  Statistical decision theory : estimation, testing, and selection , 2008 .

[15]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[16]  Tom Goldstein,et al.  PhaseMax: Convex Phase Retrieval via Basis Pursuit , 2016, IEEE Transactions on Information Theory.

[17]  J R Fienup,et al.  Phase retrieval algorithms: a comparison. , 1982, Applied optics.

[18]  Christos Thrampoulidis,et al.  Asymptotically exact error analysis for the generalized equation-LASSO , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[19]  Babak Hassibi,et al.  Sparse phase retrieval: Convex algorithms and limitations , 2013, 2013 IEEE International Symposium on Information Theory.

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

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

[22]  Christos Thrampoulidis,et al.  LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements , 2015, NIPS.

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

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

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