Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 12 min ago
PreprintarXiv licencearXiv

Optimal dimension growth rates in the high dimensional Central Limit Theorems

Abstract

We investigate the optimal dimension growth rates for the high-dimensional Central Limit Theorem (CLT) over half spaces, Euclidean balls and Borel convex sets, under the existence of fourth moments. It has been observed in the literature that d=o(nc) with 0< c≤ 1/2 is sufficient for the CLT to hold over Euclidean balls. As a consequence, the CLT over half spaces should ideally hold under similar dimension growth rates. In case of Borel convex sets, however d= o(nc) with 0< c≤ 2/5 is generally sufficient. The most recent results for CLT over Euclidean balls and Borel convex sets with respective rates d= o(√n) and d= o(n2/5) is due to Fang and Koike (2024) and under the existence of fourth moments. In this paper, we investigate whether these sufficient growth rates of d with respect to n are also necessary. Thus, our results completely characterize the sharpness of dimension growth rates under existence of fourth moments across half-spaces, Euclidean balls, and Borel convex sets.

Related

  1. Optimal Rates in Local and Central Limit Theorems for the Elephant Random Walk
    Hideki Murahara, Go Tokumitsu
    arXivPreprintarXiv licenceFull textProbabilityarXiv
  2. Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport
    Kim Jakwang, Kwon Dohyun
    arXivPreprintCC BY 4.0Full textProbabilityStatisticsarXiv
  3. Central Limit Theorems for Optimal Transport Functionals
    Haruki Kono
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  4. Central limit theorems and bootstrap for sparse regularized multimarginal optimal transport and barycenters
    Pengtao Li, Alberto González-Sanz, Xiaohui Chen
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  5. Central limit theorems for high-dimensional ridge regression under uniform subsampling
    Thomas Lam, Nina Dörnemann, Holger Dette
    arXivPreprintarXiv licenceFull textStatisticsarXiv
BibTeX
@misc{choudhury2026optimal,
  title = {{Optimal dimension growth rates in the high dimensional Central Limit Theorems}},
  author = {Mayukh Choudhury and Debraj Das},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.24183},
  eprint = {2610.24183},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.24183},
}
RIS
TY  - UNPB
TI  - Optimal dimension growth rates in the high dimensional Central Limit Theorems
AU  - Mayukh Choudhury
AU  - Debraj Das
PY  - 2026
DA  - 2026/10/16
PB  - arXiv
DO  - 10.48550/arxiv.2610.24183
UR  - https://arxiv.org/abs/2610.24183
AB  - We investigate the optimal dimension growth rates for the high-dimensional Central Limit Theorem (CLT) over half spaces, Euclidean balls and Borel convex sets, under the existence of fourth moments. It has been observed in the literature that d=o(n^c) with 0< c≤ 1/2 is sufficient for the CLT to hold over Euclidean balls. As a consequence, the CLT over half spaces should ideally hold under similar dimension growth rates. In case of Borel convex sets, however d= o(n^c) with 0< c≤ 2/5 is generally sufficient. The most recent results for CLT over Euclidean balls and Borel convex sets with respective rates d= o(√n) and d= o(n^2/5) is due to Fang and Koike (2024) and under the existence of fourth moments. In this paper, we investigate whether these sufficient growth rates of d with respect to n are also necessary. Thus, our results completely characterize the sharpness of dimension growth rates under existence of fourth moments across half-spaces, Euclidean balls, and Borel convex sets.
ER  -