Paperlane

no. 15 · Monday 16 November 2026

High-Dimensional Gaussian and Bootstrap Approximation: Near $1/\sqrt{n}$ Rates with General Covariance

Miles E. Lopes and Ricardo Masini

math.ST · 42 pp

Abstract

We consider Berry-Esseen bounds over rectangles for sums of $n$ random vectors in $\mathbb{R}^p$ that are i.i.d. A longstanding open question in high-dimensional probability and statistics is whether bounds of order $1/\sqrt n$ are attainable up to factors of $\log(pn)$ when the population covariance matrix is unrestricted. We answer this question affirmatively, provided that the random vectors have sub-Gaussian entries with non-zero variance. In addition, we provide analogous results for bootstrap approximation and Gaussian comparison, which make use of a special discrepancy measure between covariance matrices that enables improvement with respect to prior work. Taking an approach based on interpolation, the novel aspects of the proofs deal with bounding the interpolation derivatives in a way that is not sensitive to the covariance structure.

comments
42 pages
fields
Statistics Theory, Probability
pdf ↗ page arXiv:2611.17923 ↗