Phase retrieval with semi-algebraic and ReLU neural network priors

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bendory, Tamir, Dym, Nadav, Edidin, Dan, Suresh, Arun
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912351420153856
author Bendory, Tamir
Dym, Nadav
Edidin, Dan
Suresh, Arun
author_facet Bendory, Tamir
Dym, Nadav
Edidin, Dan
Suresh, Arun
contents The key ingredient to retrieving a signal from its Fourier magnitudes, namely, to solve the phase retrieval problem, is an effective prior on the sought signal. In this paper, we study the phase retrieval problem under the prior that the signal lies in a semi-algebraic set. This is a very general prior as semi-algebraic sets include linear models, sparse models, and ReLU neural network generative models. The latter is the main motivation of this paper, due to the remarkable success of deep generative models in a variety of imaging tasks, including phase retrieval. We prove that almost all signals in R^N can be determined from their Fourier magnitudes, up to a sign, if they lie in a (generic) semi-algebraic set of dimension N/2. The same is true for all signals if the semi-algebraic set is of dimension N/4. We also generalize these results to the problem of signal recovery from the second moment in multi-reference alignment models with multiplicity free representations of compact groups. This general result is then used to derive improved sample complexity bounds for recovering band-limited functions on the sphere from their noisy copies, each acted upon by a random element of SO(3).
format Preprint
id arxiv_https___arxiv_org_abs_2311_08833
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Phase retrieval with semi-algebraic and ReLU neural network priors
Bendory, Tamir
Dym, Nadav
Edidin, Dan
Suresh, Arun
Signal Processing
Information Theory
The key ingredient to retrieving a signal from its Fourier magnitudes, namely, to solve the phase retrieval problem, is an effective prior on the sought signal. In this paper, we study the phase retrieval problem under the prior that the signal lies in a semi-algebraic set. This is a very general prior as semi-algebraic sets include linear models, sparse models, and ReLU neural network generative models. The latter is the main motivation of this paper, due to the remarkable success of deep generative models in a variety of imaging tasks, including phase retrieval. We prove that almost all signals in R^N can be determined from their Fourier magnitudes, up to a sign, if they lie in a (generic) semi-algebraic set of dimension N/2. The same is true for all signals if the semi-algebraic set is of dimension N/4. We also generalize these results to the problem of signal recovery from the second moment in multi-reference alignment models with multiplicity free representations of compact groups. This general result is then used to derive improved sample complexity bounds for recovering band-limited functions on the sphere from their noisy copies, each acted upon by a random element of SO(3).
title Phase retrieval with semi-algebraic and ReLU neural network priors
topic Signal Processing
Information Theory
url https://arxiv.org/abs/2311.08833