A Sample Efficient Alternating Minimization-based Algorithm For Robust Phase Retrieval

TL;DR

This paper introduces a robust, efficient alternating minimization algorithm for phase retrieval that handles corrupted measurements without spectral initialization, ensuring convergence with nearly linear sample complexity.

Contribution

It presents a novel alternating minimization method with an oracle solver that avoids spectral initialization and provides theoretical guarantees under corrupted measurement models.

Findings

Guarantees convergence to the true signal under corruption.

Achieves nearly linear sample complexity in dimension.

Provides geometric insights into the loss landscape with corrupted data.

Abstract

In this work, we study the robust phase retrieval problem where the task is to recover an unknown signal $\theta^* \in \mathbb{R}^d$ in the presence of potentially arbitrarily corrupted magnitude-only linear measurements. We propose an alternating minimization approach that incorporates an oracle solver for a non-convex optimization problem as a subroutine. Our algorithm guarantees convergence to $\theta^*$ and provides an explicit polynomial dependence of the convergence rate on the fraction of corrupted measurements. We then provide an efficient construction of the aforementioned oracle under a sparse arbitrary outliers model and offer valuable insights into the geometric properties of the loss landscape in phase retrieval with corrupted measurements. Our proposed oracle avoids the need for computationally intensive spectral initialization, using a simple gradient descent algorithm with a constant step size and random initialization instead. Additionally, our overall algorithm achieves nearly linear sample complexity, $\mathcal{O}(d \, \mathrm{polylog}(d))$.