English

Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles

Statistics Theory 2022-03-08 v3 Probability Statistics Theory

Abstract

Let X1,,XnX_1,\dots,X_n be independent centered random vectors in Rd\mathbb{R}^d. This paper shows that, even when dd may grow with nn, the probability P(n1/2i=1nXiA)P(n^{-1/2}\sum_{i=1}^nX_i\in A) can be approximated by its Gaussian analog uniformly in hyperrectangles AA in Rd\mathbb{R}^d as nn\to\infty under appropriate moment assumptions, as long as (logd)5/n0(\log d)^5/n\to0. This improves a result of Chernozhukov, Chetverikov & Kato [Ann. Probab. 45 (2017) 2309-2353] in terms of the dimension growth condition. When n1/2i=1nXin^{-1/2}\sum_{i=1}^nX_i has a common factor across the components, this condition can be further improved to (logd)3/n0(\log d)^3/n\to0. The corresponding bootstrap approximation results are also developed. These results serve as a theoretical foundation of simultaneous inference for high-dimensional models.

Keywords

Cite

@article{arxiv.1911.00160,
  title  = {Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles},
  author = {Yuta Koike},
  journal= {arXiv preprint arXiv:1911.00160},
  year   = {2022}
}

Comments

33 pages. The constant of Lemma 2.2 is modified and the proof is corrected

R2 v1 2026-06-23T12:01:45.592Z