Phase Retrieval of Low-Rank Matrices by Anchored Regression

TL;DR

This paper introduces a convex optimization approach using anchored regression to recover low-rank matrices from phaseless measurements, with theoretical guarantees for specific structured scenarios.

Contribution

It proposes a novel convex relaxation method for low-rank phase retrieval, analyzing its effectiveness in structured cases and providing ways to construct necessary anchor matrices.

Findings

Accurate recovery with near-optimal measurements in rank-1 case.

Effective convex program for general rank matrices.

Method to construct anchor matrices from measurements.

Abstract

We study the low-rank phase retrieval problem, where we try to recover a $d_1\times d_2$ low-rank matrix from a series of phaseless linear measurements. This is a fourth-order inverse problem, as we are trying to recover factors of matrix that have been put through a quadratic nonlinearity after being multiplied together. We propose a solution to this problem using the recently introduced technique of anchored regression. This approach uses two different types of convex relaxations: we replace the quadratic equality constraints for the phaseless measurements by a search over a polytope, and enforce the rank constraint through nuclear norm regularization. The result is a convex program that works in the space of $d_1 \times d_2$ matrices. We analyze two specific scenarios. In the first, the target matrix is rank-$1$, and the observations are structured to correspond to a phaseless blind deconvolution. In the second, the target matrix has general rank, and we observe the magnitudes of the inner products against a series of independent Gaussian random matrices. In each of these problems, we show that the anchored regression returns an accurate estimate from a near-optimal number of measurements given that we have access to an anchor matrix of sufficient quality. We also show how to create such an anchor in the phaseless blind deconvolution problem, again from an optimal number of measurements, and present a partial result in this direction for the general rank problem.