English

Construction of optimal spectral methods in phase retrieval

Information Theory 2022-10-03 v3 Disordered Systems and Neural Networks math.IT

Abstract

We consider the phase retrieval problem, in which the observer wishes to recover a nn-dimensional real or complex signal X\mathbf{X}^\star from the (possibly noisy) observation of ΦX|\mathbf{\Phi} \mathbf{X}^\star|, in which Φ\mathbf{\Phi} is a matrix of size m×nm \times n. We consider a \emph{high-dimensional} setting where n,mn,m \to \infty with m/n=O(1)m/n = \mathcal{O}(1), and a large class of (possibly correlated) random matrices Φ\mathbf{\Phi} and observation channels. Spectral methods are a powerful tool to obtain approximate observations of the signal X\mathbf{X}^\star 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 Φ\mathbf{\Phi}, in an automated manner (i.e. with no optimization over any hyperparameter or preprocessing function).

Keywords

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

R2 v1 2026-06-23T20:49:11.248Z