High-dimensional Gaussian and bootstrap approximations for robust means

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kock, Anders Bredahl, Preinerstorfer, David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912983208165376
author Kock, Anders Bredahl
Preinerstorfer, David
author_facet Kock, Anders Bredahl
Preinerstorfer, David
contents Recent years have witnessed much progress on Gaussian and bootstrap approximations to the distribution of sums of independent random vectors with dimension $d$ large relative to the sample size $n$. However, for any number of moments $m>2$ that the summands may possess, there exist distributions such that these approximations break down if $d$ grows faster than the polynomial barrier $n^{\frac{m}{2}-1}$. In this paper, we establish Gaussian and bootstrap approximations to the distributions of winsorized and trimmed means that allow $d$ to grow at an exponential rate in $n$ as long as $m>2$ moments exist. The approximations remain valid under some amount of adversarial contamination. Our implementations of the winsorized and trimmed means do not require knowledge of $m$. As a consequence, the performance of the approximation guarantees ``adapts'' to $m$.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-dimensional Gaussian and bootstrap approximations for robust means
Kock, Anders Bredahl
Preinerstorfer, David
Statistics Theory
Recent years have witnessed much progress on Gaussian and bootstrap approximations to the distribution of sums of independent random vectors with dimension $d$ large relative to the sample size $n$. However, for any number of moments $m>2$ that the summands may possess, there exist distributions such that these approximations break down if $d$ grows faster than the polynomial barrier $n^{\frac{m}{2}-1}$. In this paper, we establish Gaussian and bootstrap approximations to the distributions of winsorized and trimmed means that allow $d$ to grow at an exponential rate in $n$ as long as $m>2$ moments exist. The approximations remain valid under some amount of adversarial contamination. Our implementations of the winsorized and trimmed means do not require knowledge of $m$. As a consequence, the performance of the approximation guarantees ``adapts'' to $m$.
title High-dimensional Gaussian and bootstrap approximations for robust means
topic Statistics Theory
url https://arxiv.org/abs/2504.08435