EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains

Yixuan Zhang, Qiaomin Xie

ACM SIGMETRICS Performance Evaluation Review · 20.07.2026 · 54 (1) · 216-218

DOI: 10.1145/3820171.3806885 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM SIGMETRICS Performance Evaluation Review, online erschienen am 27.07.2026. Verfasst von Yixuan Zhang und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF (National Science Foundation).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Non-asymptotic central limit theorem (CLT) rates play a central role in modern machine learning. In this paper, we study CLT rates for multivariate dependent data in Wasserstein- p (W p ) distance, for general p ≥ 1. We focus on two fundamental dependence structures that commonly arise in machine learning: locally dependent sequences and geometrically ergodic Markov chains. In both settings, we establish the first optimal O(n -1/2 ) rate in W 1 , as well as the first W p (p ≥ 2) CLT rates under mild moment assumptions, substantially improving the best previously known bounds in these dependent-data regimes. As an application of our optimal W 1 rate for locally dependent sequences, we further obtain the first optimal W 1 -CLT rate for multivariate U -statistics. On the technical side, we derive a tractable auxiliary bound for W 1 Gaussian approximation errors that is well suited for studying dependent data. For Markov chains, we further prove that the regeneration time of the split chain associated with a geometrically ergodic chain has a geometric tail without assuming strong aperiodicity or other restrictive conditions. These tools may be of independent interests and enable our optimal W 1 rates and underpin our W p (p ≥ 2) results.

Förderung

  • NSF (National Science Foundation)

Zitieren

APA

Zhang, Y., & Xie, Q. (2026). Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains. ACM SIGMETRICS Performance Evaluation Review, 54(1), 216-218. https://doi.org/10.1145/3820171.3806885

Vancouver

Zhang Y, Xie Q. Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains. ACM SIGMETRICS Performance Evaluation Review. 2026;54(1):216-218. doi:10.1145/3820171.3806885

BibTeX
@article{Zhang2026,
  author = {Zhang, Yixuan and Xie, Qiaomin},
  title = {Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains},
  journal = {ACM SIGMETRICS Performance Evaluation Review},
  year = {2026},
  volume = {54},
  number = {1},
  pages = {216--218},
  doi = {10.1145/3820171.3806885}
}
Kostenlos starten →