A Fast and Provable Algorithm for Sparse Phase Retrieval

TL;DR

This paper introduces a second-order Newton-type algorithm with hard thresholding for sparse phase retrieval, achieving quadratic convergence and outperforming existing first-order methods in speed.

Contribution

The paper presents a novel second-order algorithm with theoretical guarantees for quadratic convergence in sparse phase retrieval, improving upon the linear convergence of prior methods.

Findings

Quadratic convergence rate after logarithmic iterations.

Requires $ ext{O}(s^2 ext{log} n)$ Gaussian samples.

Numerical experiments demonstrate faster convergence than existing methods.

Abstract

We study the sparse phase retrieval problem, which seeks to recover a sparse signal from a limited set of magnitude-only measurements. In contrast to prevalent sparse phase retrieval algorithms that primarily use first-order methods, we propose an innovative second-order algorithm that employs a Newton-type method with hard thresholding. This algorithm overcomes the linear convergence limitations of first-order methods while preserving their hallmark per-iteration computational efficiency. We provide theoretical guarantees that our algorithm converges to the $s$-sparse ground truth signal $\mathbf{x}^{\natural} \in \mathbb{R}^n$ (up to a global sign) at a quadratic convergence rate after at most $O(\log (\Vert\mathbf{x}^{\natural} \Vert /x_{\min}^{\natural}))$ iterations, using $\Omega(s^2\log n)$ Gaussian random samples. Numerical experiments show that our algorithm achieves a significantly faster convergence rate than state-of-the-art methods.