A Fast and Provable Algorithm for Sparse Phase Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Jian-Feng, Long, Yu, Wen, Ruixue, Ying, Jiaxi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913271016062976
author Cai, Jian-Feng
Long, Yu
Wen, Ruixue
Ying, Jiaxi
author_facet Cai, Jian-Feng
Long, Yu
Wen, Ruixue
Ying, Jiaxi
contents 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 $Ω(s^2\log n)$ Gaussian random samples. Numerical experiments show that our algorithm achieves a significantly faster convergence rate than state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2309_02046
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Fast and Provable Algorithm for Sparse Phase Retrieval
Cai, Jian-Feng
Long, Yu
Wen, Ruixue
Ying, Jiaxi
Information Theory
Optimization and Control
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 $Ω(s^2\log n)$ Gaussian random samples. Numerical experiments show that our algorithm achieves a significantly faster convergence rate than state-of-the-art methods.
title A Fast and Provable Algorithm for Sparse Phase Retrieval
topic Information Theory
Optimization and Control
url https://arxiv.org/abs/2309.02046