Smoothed Robust Phase Retrieval

TL;DR

This paper introduces a smoothed loss function for robust phase retrieval that improves understanding of its geometric landscape, guarantees global optimality in noiseless and corrupted settings, and demonstrates efficient convergence.

Contribution

It provides the first geometric landscape analysis of phase retrieval with corruptions and proposes a smoothed approach with provable guarantees and practical effectiveness.

Findings

No spurious local solutions in noiseless case.

Benign landscape under arbitrary corruptions.

Linear convergence of gradient descent.

Abstract

The phase retrieval problem in the presence of noise aims to recover the signal vector of interest from a set of quadratic measurements with infrequent but arbitrary corruptions, and it plays an important role in many scientific applications. However, the essential geometric structure of the nonconvex robust phase retrieval based on the $\ell_1$-loss is largely unknown to study spurious local solutions, even under the ideal noiseless setting, and its intrinsic nonsmooth nature also impacts the efficiency of optimization algorithms. This paper introduces the smoothed robust phase retrieval (SRPR) based on a family of convolution-type smoothed loss functions. Theoretically, we prove that the SRPR enjoys a benign geometric structure with high probability: (1) under the noiseless situation, the SRPR has no spurious local solutions, and the target signals are global solutions, and (2) under the infrequent but arbitrary corruptions, we characterize the stationary points of the SRPR and prove its benign landscape, which is the first landscape analysis of phase retrieval with corruption in the literature. Moreover, we prove the local linear convergence rate of gradient descent for solving the SRPR under the noiseless situation. Experiments on both simulated datasets and image recovery are provided to demonstrate the numerical performance of the SRPR.