Optimal Rates of Convergence for Noisy Sparse Phase Retrieval via Thresholded Wirtinger Flow

06/10/2015
by   T. Tony Cai, et al.
0

This paper considers the noisy sparse phase retrieval problem: recovering a sparse signal x ∈R^p from noisy quadratic measurements y_j = (a_j' x )^2 + ϵ_j, j=1, ..., m, with independent sub-exponential noise ϵ_j. The goals are to understand the effect of the sparsity of x on the estimation precision and to construct a computationally feasible estimator to achieve the optimal rates. Inspired by the Wirtinger Flow [12] proposed for noiseless and non-sparse phase retrieval, a novel thresholded gradient descent algorithm is proposed and it is shown to adaptively achieve the minimax optimal rates of convergence over a wide range of sparsity levels when the a_j's are independent standard Gaussian random vectors, provided that the sample size is sufficiently large compared to the sparsity of x.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/08/2021

Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent

This paper studies early-stopped mirror descent applied to noisy sparse ...
research
12/14/2016

Efficient phase retrieval based on dark fringe recognition with an ability of bypassing invalid fringes

This paper discusses the noisy phase retrieval problem: recovering a com...
research
04/20/2017

Robust Wirtinger Flow for Phase Retrieval with Arbitrary Corruption

We consider the phase retrieval problem of recovering the unknown signal...
research
10/20/2020

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval

We analyze continuous-time mirror descent applied to sparse phase retrie...
research
03/21/2018

Gradient Descent with Random Initialization: Fast Global Convergence for Nonconvex Phase Retrieval

This paper considers the problem of solving systems of quadratic equatio...
research
05/27/2022

Error Bound of Empirical ℓ_2 Risk Minimization for Noisy Standard and Generalized Phase Retrieval Problems

A noisy generalized phase retrieval (NGPR) problem refers to a problem o...
research
02/12/2018

Some effects in adaptive robust estimation under sparsity

Adaptive estimation in the sparse mean model and in sparse regression ex...

Please sign up or login with your details

Forgot password? Click here to reset