Construction of optimal spectral methods in phase retrieval

by   Antoine Maillard, et al.

We consider the phase retrieval problem, in which the observer wishes to recover a n-dimensional real or complex signal 𝐗^⋆ from the (possibly noisy) observation of |Φ𝐗^⋆|, in which Ξ¦ is a matrix of size m Γ— n. We consider a high-dimensional setting where n,m β†’βˆž with m/n = π’ͺ(1), and a large class of (possibly correlated) random matrices Ξ¦ and observation channels. Spectral methods are a powerful tool to obtain approximate observations of the signal 𝐗^⋆ which can be then used as initialization for a subsequent algorithm, at a low computational cost. In this paper, we extend and unify previous results and approaches on spectral methods for the phase retrieval problem. More precisely, we combine the linearization of message-passing algorithms and the analysis of the Bethe Hessian, a classical tool of statistical physics. Using this toolbox, we show how to derive optimal spectral methods for arbitrary channel noise and right-unitarily invariant matrix Ξ¦, in an automated manner (i.e. with no optimization over any hyperparameter or preprocessing function).



page 12

page 13

page 21

βˆ™ 06/09/2020

Phase retrieval in high dimensions: Statistical and computational phase transitions

We consider the phase retrieval problem of reconstructing a n-dimensiona...
βˆ™ 10/07/2020

Approximate Message Passing with Spectral Initialization for Generalized Linear Models

We consider the problem of estimating a signal from measurements obtaine...
βˆ™ 08/24/2020

Universality of Linearized Message Passing for Phase Retrieval with Structured Sensing Matrices

In the phase retrieval problem one seeks to recover an unknown n dimensi...
βˆ™ 03/07/2019

Rigorous Analysis of Spectral Methods for Random Orthogonal Matrices

Phase retrieval refers to algorithmic methods for recovering a signal fr...
βˆ™ 06/08/2018

Approximate Message Passing for Amplitude Based Optimization

We consider an β„“_2-regularized non-convex optimization problem for recov...
βˆ™ 03/15/2022

Optimal denoising of rotationally invariant rectangular matrices

In this manuscript we consider denoising of large rectangular matrices: ...
βˆ™ 05/13/2019

Generalized Approximate Survey Propagation for High-Dimensional Estimation

In Generalized Linear Estimation (GLE) problems, we seek to estimate a s...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.