Misspecified Nonconvex Statistical Optimization for Phase Retrieval

12/18/2017
by   Zhuoran Yang, et al.
0

Existing nonconvex statistical optimization theory and methods crucially rely on the correct specification of the underlying "true" statistical models. To address this issue, we take a first step towards taming model misspecification by studying the high-dimensional sparse phase retrieval problem with misspecified link functions. In particular, we propose a simple variant of the thresholded Wirtinger flow algorithm that, given a proper initialization, linearly converges to an estimator with optimal statistical accuracy for a broad family of unknown link functions. We further provide extensive numerical experiments to support our theoretical findings.

READ FULL TEXT
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
06/02/2016

High Dimensional Multivariate Regression and Precision Matrix Estimation via Nonconvex Optimization

We propose a nonconvex estimator for joint multivariate regression and p...
research
10/11/2022

Misspecified Phase Retrieval with Generative Priors

In this paper, we study phase retrieval under model misspecification and...
research
06/14/2019

A stochastic alternating minimizing method for sparse phase retrieval

Sparse phase retrieval plays an important role in many fields of applied...
research
12/23/2014

Pathwise Coordinate Optimization for Sparse Learning: Algorithm and Theory

The pathwise coordinate optimization is one of the most important comput...
research
03/04/2015

Statistical Limits of Convex Relaxations

Many high dimensional sparse learning problems are formulated as nonconv...
research
01/30/2018

An Incremental Path-Following Splitting Method for Linearly Constrained Nonconvex Nonsmooth Programs

The linearly constrained nonconvex nonsmooth program has drawn much atte...

Please sign up or login with your details

Forgot password? Click here to reset