Construction of optimal spectral methods in phase retrieval
Abstract
We consider the phase retrieval problem, in which the observer wishes to recover a -dimensional real or complex signal from the (possibly noisy) observation of , in which is a matrix of size . We consider a \emph{high-dimensional} setting where with , and a large class of (possibly correlated) random matrices and observation channels. Spectral methods are a powerful tool to obtain approximate observations of the signal 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 \emph{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 , in an automated manner (i.e. with no optimization over any hyperparameter or preprocessing function).
Cite
@article{arxiv.2012.04524,
title = {Construction of optimal spectral methods in phase retrieval},
author = {Antoine Maillard and Florent Krzakala and Yue M. Lu and Lenka Zdeborová},
journal= {arXiv preprint arXiv:2012.04524},
year = {2022}
}
Comments
14 pages + references and appendix. v2: Version updated to match the one accepted at MSML 2021. v3: Adding a reference to a previous work mentioning marginal stability and its connection to Bayes-optimality