Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations

We study the phase retrieval problem, which solves quadratic system of equations, i.e., recovers a vector $\boldsymbol{x}\in \mathbb{R}^n$ from its magnitude measurements $y_i=|\langle \boldsymbol{a}_i, \boldsymbol{x}\rangle|, i=1,..., m$. We develop a gradient-like algorithm (referred to as RWF representing reshaped Wirtinger flow) by minimizing a nonconvex nonsmooth loss function. In comparison with existing nonconvex Wirtinger flow (WF) algorithm \cite{candes2015phase}, although the loss function becomes nonsmooth, it involves only the second power of variable and hence reduces the complexity. We show that for random Gaussian measurements, RWF enjoys geometric convergence to a global optimal point as long as the number $m$ of measurements is on the order of $n$, the dimension of the unknown $\boldsymbol{x}$. This improves the sample complexity of WF, and achieves the same sample complexity as truncated Wirtinger flow (TWF) \cite{chen2015solving}, but without truncation in gradient loop. Furthermore, RWF costs less computationally than WF, and runs faster numerically than both WF and TWF. We further develop the incremental (stochastic) reshaped Wirtinger flow (IRWF) and show that IRWF converges linearly to the true signal. We further establish performance guarantee of an existing Kaczmarz method for the phase retrieval problem based on its connection to IRWF. We also empirically demonstrate that IRWF outperforms existing ITWF algorithm (stochastic version of TWF) as well as other batch algorithms.

[1]  J. D. Donahue PRODUCTS AND QUOTIENTS OF RANDOM VARIABLES AND THEIR APPLICATIONS , 1964 .

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

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

[4]  J. Miao,et al.  Extending the methodology of X-ray crystallography to allow imaging of micrometre-sized non-crystalline specimens , 1999, Nature.

[5]  A. Föhrenbach,et al.  SIMPLE++ , 2000, OR Spectr..

[6]  Jan Drenth,et al.  X‐Ray Crystallography , 2002 .

[7]  A. Kruger On Fréchet Subdifferentials , 2003 .

[8]  Adrian S. Lewis,et al.  A Robust Gradient Sampling Algorithm for Nonsmooth, Nonconvex Optimization , 2005, SIAM J. Optim..

[9]  Krzysztof C. Kiwiel,et al.  Convergence of the Gradient Sampling Algorithm for Nonsmooth Nonconvex Optimization , 2007, SIAM J. Optim..

[10]  R. Vershynin,et al.  A Randomized Kaczmarz Algorithm with Exponential Convergence , 2007, math/0702226.

[11]  J. Miao,et al.  Extending X-ray crystallography to allow the imaging of noncrystalline materials, cells, and single protein complexes. , 2008, Annual review of physical chemistry.

[12]  Andrea Montanari,et al.  Matrix completion from a few entries , 2009, ISIT.

[13]  G. Papanicolaou,et al.  Array imaging using intensity-only measurements , 2010 .

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

[15]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[16]  Eric Moulines,et al.  Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning , 2011, NIPS.

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

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Jianqing Fan,et al.  Distributions of angles in random packing on spheres , 2013, J. Mach. Learn. Res..

[20]  Nikolaos M. Freris,et al.  Randomized Extended Kaczmarz for Solving Least Squares , 2012, SIAM J. Matrix Anal. Appl..

[21]  Prateek Jain,et al.  Low-rank matrix completion using alternating minimization , 2012, STOC '13.

[22]  Deanna Needell,et al.  Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm , 2013, Mathematical Programming.

[23]  Prateek Jain,et al.  Non-convex Robust PCA , 2014, NIPS.

[24]  Felix Krahmer,et al.  Improved Recovery Guarantees for Phase Retrieval from Coded Diffraction Patterns , 2014, arXiv.org.

[25]  Moritz Hardt,et al.  Understanding Alternating Minimization for Matrix Completion , 2013, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

[26]  Zhiqiang Xu,et al.  The minimal measurement number for low-rank matrices recovery , 2015, ArXiv.

[27]  Yuantao Gu,et al.  Phase retrieval using iterative projections: Dynamics in the large systems limit , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[28]  Thomas Brox,et al.  On Iteratively Reweighted Algorithms for Nonsmooth Nonconvex Optimization in Computer Vision , 2015, SIAM J. Imaging Sci..

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

[30]  Sanjeev Arora,et al.  Simple, Efficient, and Neural Algorithms for Sparse Coding , 2015, COLT.

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

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

[33]  Zhi-Quan Luo,et al.  Guaranteed Matrix Completion via Non-Convex Factorization , 2014, IEEE Transactions on Information Theory.

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

[35]  Ke Wei Solving systems of phaseless equations via Kaczmarz methods: a proof of concept study , 2015 .

[36]  John D. Lafferty,et al.  A Convergent Gradient Descent Algorithm for Rank Minimization and Semidefinite Programming from Random Linear Measurements , 2015, NIPS.

[37]  Yonina C. Eldar,et al.  Phase Retrieval with Application to Optical Imaging: A contemporary overview , 2015, IEEE Signal Processing Magazine.

[38]  Furong Huang,et al.  Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition , 2015, COLT.

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

[40]  Christopher De Sa,et al.  Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems , 2014, ICML.

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

[42]  John Wright,et al.  Complete Dictionary Recovery Using Nonconvex Optimization , 2015, ICML.

[43]  Martin J. Wainwright,et al.  Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees , 2015, ArXiv.

[44]  Yingbin Liang,et al.  Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow , 2016, ICML.

[45]  Ayfer Özgür,et al.  Phase Retrieval via Incremental Truncated Wirtinger Flow , 2016, ArXiv.

[46]  John Wright,et al.  A Geometric Analysis of Phase Retrieval , 2016, International Symposium on Information Theory.

[47]  John D. Lafferty,et al.  Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent , 2016, ArXiv.

[48]  Nathan Srebro,et al.  Global Optimality of Local Search for Low Rank Matrix Recovery , 2016, NIPS.

[49]  Yuejie Chi,et al.  Kaczmarz Method for Solving Quadratic Equations , 2016, IEEE Signal Processing Letters.

[50]  Sham M. Kakade,et al.  Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent , 2016, NIPS.

[51]  Nicolas Boumal,et al.  On the low-rank approach for semidefinite programs arising in synchronization and community detection , 2016, COLT.

[52]  Prateek Jain,et al.  Tensor vs. Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations , 2015, AISTATS.

[53]  Alexandre d'Aspremont,et al.  Phase retrieval for imaging problems , 2013, Mathematical Programming Computation.

[54]  Anastasios Kyrillidis,et al.  Provable non-convex projected gradient descent for a class of constrained matrix optimization problems , 2016, ArXiv.

[55]  Michael I. Jordan,et al.  Gradient Descent Converges to Minimizers , 2016, ArXiv.

[56]  Tengyu Ma,et al.  Matrix Completion has No Spurious Local Minimum , 2016, NIPS.

[57]  Max Simchowitz,et al.  Low-rank Solutions of Linear Matrix Equations via Procrustes Flow , 2015, ICML.

[58]  Tony F. Chan,et al.  Guarantees of Riemannian Optimization for Low Rank Matrix Recovery , 2015, SIAM J. Matrix Anal. Appl..

[59]  Nicolas Boumal,et al.  Nonconvex Phase Synchronization , 2016, SIAM J. Optim..

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

[61]  Yuanying Chen,et al.  Rapid evolution of piRNA clusters in the Drosophila melanogaster ovary , 2023, bioRxiv.

[62]  A. Ashok Stochastic Gradient Descent for Deep Learning , 2017 .

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

[64]  Yingbin Liang,et al.  Median-Truncated Nonconvex Approach for Phase Retrieval With Outliers , 2016, IEEE Transactions on Information Theory.

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