A note on Douglas-Rachford, subgradients, and phase retrieval

11/29/2019
by   Eitan Levin, et al.
0

The properties of gradient techniques for the phase retrieval problem have received a considerable attention in recent years. In almost all applications, however, the phase retrieval problem is solved using a family of algorithms that can be interpreted as variants of Douglas-Rachford splitting. In this work, we establish a connection between Douglas-Rachford and gradient algorithms. Specifically, we show that in some cases a generalization of Douglas-Rachford, called relaxed-reflect-reflect (RRR), can be viewed as subgradient descent on a certain objective function. The solutions coincide with the critical points of that objective, which—in contrast to standard gradient techniques—are not its minimizers. Using the objective function, we analyze the RRR algorithm, describe its set of solutions, show a local convexity around any solution, and derive stability guarantees. Nevertheless, in its present state, the analysis does not elucidate the remarkable empirical performance of RRR and its global properties.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2019

Proximal gradient flow and Douglas-Rachford splitting dynamics: global exponential stability via integral quadratic constraints

Many large-scale and distributed optimization problems can be brought in...
research
05/07/2020

Phase retrieval of complex-valued objects via a randomized Kaczmarz method

This paper investigates the convergence of the randomized Kaczmarz algor...
research
03/08/2021

Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem

In this paper we investigate how gradient-based algorithms such as gradi...
research
10/22/2018

On DC based Methods for Phase Retrieval

In this paper, we develop a new computational approach which is based on...
research
07/16/2020

DeepInit Phase Retrieval

This paper shows how data-driven deep generative models can be utilized ...
research
04/20/2022

Nearly optimal bounds for the global geometric landscape of phase retrieval

The phase retrieval problem is concerned with recovering an unknown sign...
research
02/22/2016

A Geometric Analysis of Phase Retrieval

Can we recover a complex signal from its Fourier magnitudes? More genera...

Please sign up or login with your details

Forgot password? Click here to reset