Optimal rates of convergence for noisy sparse phase retrieval via thresholded Wirtinger flow

DOI10.1214/16-AOS1443zbMath1349.62019arXiv1506.03382OpenAlexW2962999772MaRDI QIDQ342686

Xiaodong Li, Zongming Ma

Publication date: 18 November 2016

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1506.03382

zbMATH Keywords

sparse recoveryphase retrievalminimax rateiterative adaptive thresholdingnon-convex empirical riskthresholded gradient method

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Applications of statistics to physics (62P35)

Related Items (30)

An optimal statistical and computational framework for generalized tensor estimation ⋮ The numerics of phase retrieval ⋮ Model-free Nonconvex Matrix Completion: Local Minima Analysis and Applications in Memory-efficient Kernel PCA ⋮ Constructing confidence intervals for the signals in sparse phase retrieval ⋮ The recovery of complex sparse signals from few phaseless measurements ⋮ Phase retrieval using alternating minimization in a batch setting ⋮ Sparse signal recovery from phaseless measurements via hard thresholding pursuit ⋮ An Efficient and Robust Scalar Auxialiary Variable Based Algorithm for Discrete Gradient Systems Arising from Optimizations ⋮ Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution ⋮ Fundamental limits of weak recovery with applications to phase retrieval ⋮ Inertial proximal ADMM for separable multi-block convex optimizations and compressive affine phase retrieval ⋮ Partially Observed Dynamic Tensor Response Regression ⋮ Phase retrieval via sparse Wirtinger flow ⋮ Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval ⋮ First-order methods almost always avoid strict saddle points ⋮ Misspecified nonconvex statistical optimization for sparse phase retrieval ⋮ Compressive phase retrieval: Optimal sample complexity with deep generative priors ⋮ Robust High-Dimensional Regression with Coefficient Thresholding and Its Application to Imaging Data Analysis ⋮ Provable sample-efficient sparse phase retrieval initialized by truncated power method ⋮ Robust amplitude method with \(L_{1/2}\)-regularization for compressive phase retrieval ⋮ Performance bounds of the intensity-based estimators for noisy phase retrieval ⋮ Phase retrieval from Fourier measurements with masks ⋮ Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics ⋮ A geometric analysis of phase retrieval ⋮ Variational Phase Retrieval with Globally Convergent Preconditioned Proximal Algorithm ⋮ Phase retrieval with PhaseLift algorithm ⋮ On DC based methods for phase retrieval ⋮ Proof methods for robust low-rank matrix recovery ⋮ Toward a Mathematical Theory of the Crystallographic Phase Retrieval Problem ⋮ ISLET: Fast and Optimal Low-Rank Tensor Regression via Importance Sketching

This page was built for publication: Optimal rates of convergence for noisy sparse phase retrieval via thresholded Wirtinger flow