Compressive Phase Retrieval: Optimal Sample Complexity with Deep Generative Priors

08/24/2020
by   Paul Hand, et al.
0

Advances in compressive sensing provided reconstruction algorithms of sparse signals from linear measurements with optimal sample complexity, but natural extensions of this methodology to nonlinear inverse problems have been met with potentially fundamental sample complexity bottlenecks. In particular, tractable algorithms for compressive phase retrieval with sparsity priors have not been able to achieve optimal sample complexity. This has created an open problem in compressive phase retrieval: under generic, phaseless linear measurements, are there tractable reconstruction algorithms that succeed with optimal sample complexity? Meanwhile, progress in machine learning has led to the development of new data-driven signal priors in the form of generative models, which can outperform sparsity priors with significantly fewer measurements. In this work, we resolve the open problem in compressive phase retrieval and demonstrate that generative priors can lead to a fundamental advance by permitting optimal sample complexity by a tractable algorithm in this challenging nonlinear inverse problem. We additionally provide empirics showing that exploiting generative priors in phase retrieval can significantly outperform sparsity priors. These results provide support for generative priors as a new paradigm for signal recovery in a variety of contexts, both empirically and theoretically. The strengths of this paradigm are that (1) generative priors can represent some classes of natural signals more concisely than sparsity priors, (2) generative priors allow for direct optimization over the natural signal manifold, which is intractable under sparsity priors, and (3) the resulting non-convex optimization problems with generative priors can admit benign optimization landscapes at optimal sample complexity, perhaps surprisingly, even in cases of nonlinear measurements.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2019

Alternating Phase Projected Gradient Descent with Generative Priors for Solving Compressive Phase Retrieval

The classical problem of phase retrieval arises in various signal acquis...
research
07/11/2018

Phase Retrieval Under a Generative Prior

The phase retrieval problem asks to recover a natural signal y_0 ∈R^n fr...
research
12/04/2019

Exact asymptotics for phase retrieval and compressed sensing with random generative priors

We consider the problem of compressed sensing and of (real-valued) phase...
research
06/29/2021

Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors

Compressive phase retrieval is a popular variant of the standard compres...
research
04/24/2022

Signal Recovery with Non-Expansive Generative Network Priors

We study compressive sensing with a deep generative network prior. Initi...
research
06/01/2020

Hadamard Wirtinger Flow for Sparse Phase Retrieval

We consider the problem of reconstructing an n-dimensional k-sparse sign...
research
09/21/2022

Autocorrelation analysis for cryo-EM with sparsity constraints: Improved sample complexity and projection-based algorithms

The number of noisy images required for molecular reconstruction in sing...

Please sign up or login with your details

Forgot password? Click here to reset