Robust Sparse Phase Retrieval: Statistical Guarantee, Optimality Theory and Convergent Algorithm

TL;DR

This paper introduces a robust sparse phase retrieval method that uses the Huber loss and $\, ext{l}_{1/2}$-norm regularization, providing statistical guarantees, optimality conditions, and a convergent algorithm, effectively handling noisy measurements.

Contribution

It proposes a novel robust sparse phase retrieval approach with theoretical guarantees and an efficient convergent algorithm, addressing noise and outliers in measurements.

Findings

Method improves robustness against noise and outliers.

Theoretical guarantees for statistical robustness and optimality.

Algorithm converges linearly under mild conditions.

Abstract

Phase retrieval (PR) is a popular research topic in signal processing and machine learning. However, its performance degrades significantly when the measurements are corrupted by noise or outliers. To address this limitation, we propose a novel robust sparse PR method that covers both real- and complex-valued cases. The core is to leverage the Huber function to measure the loss and adopt the $\ell_{1/2}$-norm regularization to realize feature selection, thereby improving the robustness of PR. In theory, we establish statistical guarantees for such robustness and derive necessary optimality conditions for global minimizers. Particularly, for the complex-valued case, we provide a fixed point inclusion property inspired by Wirtinger derivatives. Furthermore, we develop an efficient optimization algorithm by integrating the gradient descent method into a majorization-minimization (MM) framework. It is rigorously proved that the whole generated sequence is convergent and also has a linear convergence rate under mild conditions, which has not been investigated before. Numerical examples under different types of noise validate the robustness and effectiveness of our proposed method.