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

03/21/2018
by   Yuxin Chen, et al.
0

This paper considers the problem of solving systems of quadratic equations, namely, recovering an object of interest x^∈R^n from m quadratic equations/samples y_i=(a_i^x^)^2, 1≤ i≤ m. This problem, also dubbed as phase retrieval, spans multiple domains including physical sciences and machine learning. We investigate the efficiency of gradient descent (or Wirtinger flow) designed for the nonconvex least squares problem. We prove that under Gaussian designs, gradient descent --- when randomly initialized --- yields an ϵ-accurate solution in O( n+(1/ϵ)) iterations given nearly minimal samples, thus achieving near-optimal computational and sample complexities at once. This provides the first global convergence guarantee concerning vanilla gradient descent for phase retrieval, without the need of (i) carefully-designed initialization, (ii) sample splitting, or (iii) sophisticated saddle-point escaping schemes. All of these are achieved by exploiting the statistical models in analyzing optimization algorithms, via a leave-one-out approach that enables the decoupling of certain statistical dependency between the gradient descent iterates and the data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/10/2021

Solving phase retrieval with random initial guess is nearly as good as by spectral initialization

The problem of recovering a signal 𝐱∈ℝ^n from a set of magnitude measure...
research
02/17/2018

Nonconvex Matrix Factorization from Rank-One Measurements

We consider the problem of recovering low-rank matrices from random rank...
research
06/10/2015

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

This paper considers the noisy sparse phase retrieval problem: recoverin...
research
12/03/2017

Convolutional Phase Retrieval via Gradient Descent

We study the convolutional phase retrieval problem, which considers reco...
research
02/05/2018

Phase retrieval with background information

Phase retrieval problem has been studied in various applications. It is ...

Please sign up or login with your details

Forgot password? Click here to reset