Geometric Inference for General High-Dimensional Linear Inverse Problems

04/17/2014
by   T. Tony Cai, et al.
0

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 minoration estimate.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/25/2023

Statistical Inference and Large-scale Multiple Testing for High-dimensional Regression Models

This paper presents a selective survey of recent developments in statist...
research
03/27/2018

A statistical mechanics approach to de-biasing and uncertainty estimation in LASSO for random measurements

In high-dimensional statistical inference in which the number of paramet...
research
09/27/2019

On a convergence property of a geometrical algorithm for statistical manifolds

In this paper, we examine a geometrical projection algorithm for statist...
research
05/31/2021

A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees

Debiased machine learning is a meta algorithm based on bias correction a...
research
11/17/2019

Constrained High Dimensional Statistical Inference

In typical high dimensional statistical inference problems, confidence i...
research
12/16/2020

A connection between the pattern classification problem and the General Linear Model for statistical inference

A connection between the General Linear Model (GLM) in combination with ...
research
03/21/2018

From Gauss to Kolmogorov: Localized Measures of Complexity for Ellipses

The Gaussian width is a fundamental quantity in probability, statistics ...

Please sign up or login with your details

Forgot password? Click here to reset