Geometric Inference for General High-Dimensional Linear Inverse Problems

Loading...
Thumbnail Image
Penn collection
Statistics Papers
Degree type
Discipline
Subject
Physical Sciences and Mathematics
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Cai, Tony
Liang, Tengyuan
Rakhlin, Alexander
Contributor
Abstract

This paper presents a unified geometric framework for the statistical analysis of a general ill-posed linear inverse model which includes as special cases noisy compressed sensing, sign vector recovery, trace regression, orthogonal matrix estimation and noisy matrix completion. We propose computationally feasible convex programs for statistical inference including estimation, confidence intervals and hypothesis testing. A theoretical framework is developed to characterize the local estimation rate of convergence and to provide statistical inference guarantees. Our results are built based on the local conic geometry and duality. The difficulty of statistical inference is captured by the geometric characterization of the local tangent cone through the Gaussian width and Sudakov estimate.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
2016-07-01
Journal title
The Annals of Statistics
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection