Large-dimensional Central Limit Theorem with Fourth-moment Error Bounds on Convex Sets and Balls

09/01/2020
by   Xiao Fang, et al.
0

We prove the large-dimensional Gaussian approximation of a sum of n independent random vectors in ℝ^d together with fourth-moment error bounds on convex sets and Euclidean balls. We show that compared with classical third-moment bounds, our bounds can achieve improved and, in the case of balls, optimal dependence d=o(n) on dimension. We discuss an application to the bootstrap. The proof is by recent advances in Stein's method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/13/2020

Central Limit Theorem and Bootstrap Approximation in High Dimensions with Near 1/√(n) Rates

Non-asymptotic bounds for Gaussian and bootstrap approximation have rece...
research
04/25/2022

Smoothed Analysis of the Komlós Conjecture

The well-known Komlós conjecture states that given n vectors in ℝ^d with...
research
07/18/2023

Almost sharp covariance and Wishart-type matrix estimation

Let X_1,..., X_n ∈ℝ^d be independent Gaussian random vectors with indepe...
research
04/12/2018

Stein kernels and moment maps

We describe a construction of Stein kernels using moment maps, which are...
research
05/04/2018

Regularity of solutions of the Stein equation and rates in the multivariate central limit theorem

Consider the multivariate Stein equation Δ f - x·∇ f = h(x) - E h(Z), wh...
research
12/07/2020

Uniform Central Limit Theorem for self normalized sums in high dimensions

In this article, we are interested in the normal approximation of the se...
research
09/28/2020

High-dimensional CLT for Sums of Non-degenerate Random Vectors: n^-1/2-rate

In this note, we provide a Berry–Esseen bounds for rectangles in high-di...

Please sign up or login with your details

Forgot password? Click here to reset