The Estimation Performance of Nonlinear Least Squares for Phase Retrieval

DOI10.1109/TIT.2020.2983562MaRDI QIDQ5138944zbMATH OpenOpenAlexFDO

Authors Meng Huang, Zhiqiang Xu

Publication date 4 December 2020

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1904.09711

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) General nonlinear regression (62J02) Ridge regression; shrinkage estimators (Lasso) (62J07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Suppose that $mathbfy=lvertAmathbf{x}_{0}vert+eta$ where $mathbf{x}_{0}inmathbb{R}^d$ is the target signal and $etainmathbb{R}^m$ is a noise vector. The aim of phase retrieval is to estimate $mathbf{x}_0$ from $mathbfy$. A popular model for estimating $mathbf{x}_0$ is the nonlinear least square $widehatmathbfx:={margmin}_{mathbfx}|lvertAmathbfxvert-mathbfy{|}_2$. One already develops many efficient algorithms for solving the model, such as the seminal error reduction algorithm. In this paper, we present the estimation performance of the model with proving that $|widehatmathbfx-mathbf{x}_0|lesssim|eta{|}_2/sqrtm$ under the assumption of $A$ being a Gaussian random matrix. We also prove the reconstruction error $|eta{|}_2/sqrtm$ is sharp. For the case where $mathbf{x}_0$ is sparse, we study the estimation performance of both the nonlinear Lasso of phase retrieval and its unconstrained version. Our results are non-asymptotic, and we do not assume any distribution on the noise $eta$. To the best of our knowledge, our results represent the first theoretical guarantee for the nonlinear least square and for the nonlinear Lasso of phase retrieval.

Recommendations

• Phase reconstruction via nonlinear least-squares
• scientific article; zbMATH DE number 3909033
• The nonsmooth landscape of phase retrieval
• Phase retrieval for sub-Gaussian measurements
• A Deterministic Theory for Exact Non-Convex Phase Retrieval
• Non-Convex Phase Retrieval From STFT Measurements
• Phase retrieval from the magnitudes of affine linear measurements
• Phase Retrieval Algorithm via Nonconvex Minimization Using a Smoothing Function
• Polynomial Phase Estimation by Least Squares Phase Unwrapping
• Phase retrieval: stability and recovery guarantees

Cited in

(8)

• scientific article; zbMATH DE number 7255152 (Why is no real title available?)
• Phase retrieval: theory, model and algorithms
• Performance bounds of the intensity-based estimators for noisy phase retrieval
• Uniqueness and stability for the solution of a nonlinear least squares problem
• Stability in phase retrieval: characterizing condition numbers and the optimal vector set
• An oracle gradient regularized Newton method for quadratic measurements regression
• Phase retrieval of quaternion signals via augmented Gauss-Newton method
• Sparse signal recovery from phaseless measurements via _1² - _2² minimization

This page was built for publication: The Estimation Performance of Nonlinear Least Squares for Phase Retrieval

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5138944)