Compressive Phase Retrieval via Reweighted Amplitude Flow
arXiv:1712.02426 · doi:10.1109/TSP.2018.2862395
Abstract
The problem of reconstructing a sparse signal vector from magnitude-only measurements (a.k.a., compressive phase retrieval), emerges naturally in diverse applications, but it is NP-hard in general. Building on recent advances in nonconvex optimization, this paper puts forth a new algorithm that is termed compressive reweighted amplitude flow and abbreviated as CRAF, for compressive phase retrieval. Specifically, CRAF operates in two stages. The first stage seeks a sparse initial guess via a new spectral procedure. In the second stage, CRAF implements a few hard thresholding based iterations using reweighted gradients. When there are sufficient measurements, CRAF provably recovers the underlying signal vector exactly with high probability under suitable conditions. Moreover, its sample complexity coincides with that of the state-of-the-art procedures. Finally, substantial simulated tests showcase remarkable performance of the new spectral initialization, as well as improved exact recovery relative to competing alternatives.
References in corpus (14)
- Model-Based Compressive Sensing
- Phase Retrieval via Wirtinger Flow: Theory and Algorithms
- GESPAR: Efficient Phase Retrieval of Sparse Signals
- Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
- Phase Retrieval: An Overview of Recent Developments
- Phase Recovery, MaxCut and Complex Semidefinite Programming
- Phase Retrieval Meets Statistical Learning Theory: A Flexible Convex Relaxation
- Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow
- An Elementary Proof of Convex Phase Retrieval in the Natural Parameter Space via the Linear Program PhaseMax
- Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations
- Solving (most) of a set of quadratic equalities: Composite optimization for robust phase retrieval
- Randomized Block Frank-Wolfe for Convergent Large-Scale Learning
- Compressed Sensing from Phaseless Gaussian Measurements via Linear Programming in the Natural Parameter Space
- Structured signal recovery from quadratic measurements: Breaking sample complexity barriers via nonconvex optimization