DeepAI

# Quantitative limit theorems and bootstrap approximations for empirical spectral projectors

Given finite i.i.d. samples in a Hilbert space with zero mean and trace-class covariance operator Σ, the problem of recovering the spectral projectors of Σ naturally arises in many applications. In this paper, we consider the problem of finding distributional approximations of the spectral projectors of the empirical covariance operator Σ̂, and offer a dimension-free framework where the complexity is characterized by the so-called relative rank of Σ. In this setting, novel quantitative limit theorems and bootstrap approximations are presented subject only to mild conditions in terms of moments and spectral decay. In many cases, these even improve upon existing results in a Gaussian setting.

• 3 publications
• 11 publications
07/21/2021

### Approximation of SPDE covariance operators by finite elements: A semigroup approach

The problem of approximating the covariance operator of the mild solutio...
04/20/2020

### Eigenvalues of graphs and spectral Moore theorems

In this paper, we describe some recent spectral Moore theorems related t...
09/13/2019

### Bootstrapping the Operator Norm in High Dimensions: Error Estimation for Covariance Matrices and Sketching

Although the operator (spectral) norm is one of the most widely used met...
12/17/2020

### Nearly optimal central limit theorem and bootstrap approximations in high dimensions

In this paper, we derive new, nearly optimal bounds for the Gaussian app...
12/22/2019

### Improved Central Limit Theorem and bootstrap approximations in high dimensions

This paper deals with the Gaussian and bootstrap approximations to the d...
10/28/2020

### Tangent fields, intrinsic stationarity, and self-similarity

This paper studies the local structure of continuous random fields on ℝ^...
08/05/2022

### Improved Rates of Bootstrap Approximation for the Operator Norm: A Coordinate-Free Approach

Let Σ̂=1/n∑_i=1^n X_i⊗ X_i denote the sample covariance operator of cent...