arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.09480math.PRcs.LGstat.ML

一致遍历马尔可夫链的多变量鞅和的高斯近似

Gaussian Approximation for Multivariate Martingale Sums from Uniformly Ergodic Markov Chains

Yixuan Zhang, Qiaomin Xie

首次发表
浏览论文内容

中文总结 AI 辅助

针对一致遍历马尔可夫链的多变量鞅和,提出高阶Wasserstein距离下的高斯近似界,在平衡增量情形下达到最优$O(n^{-1/2})$速率,并开发了两种新技术处理时间依赖性。

中文摘要 AI 辅助

我们针对由一致遍历马尔可夫链生成的多变量鞅差之和,建立了高阶Wasserstein距离$W_p$($p\geq2$)下的高斯近似界。在$\eta>0$的$L^{(2+\eta)p}$矩条件下,我们得到了显式界 $$ O\left( p^3 \\|A\\|_4^2 + pd^{1/4}\\|A\\|_2^{1/2}\\|A\\|_4^2 \right) $$ 其中$A\in\mathbb{R}^n$收集了$n$个单个鞅增量的$L^{(2+\eta)p}$大小。在平衡增量情形下,即单个增量具有$n^{-1/2}$量级的可比大小时,对于固定的$p$和$d$,这给出了首个最优的$O(n^{-1/2})$高斯近似速率。因此,我们也获得了一致遍历马尔可夫链的多变量加性泛函的首个最优$O(n^{-1/2})$ $W_p$高斯近似速率。我们的分析开发了两种技术来处理高阶Wasserstein距离与时间依赖性之间的相互作用。首先,基于Fang和Koike(2023)的Ornstein--Uhlenbeck相对得分方法,我们在保留条件张量结构的同时,用反对称Stein耦合来表述该界。其次,我们开发了一种刷新-然后-最大耦合方法,该方法结合了独立的第一步重采样(保留了所需的Stein恒等式)和随后的最大耦合(对耦合增量提供有效控制)。这些工具可能更广泛地用于时间依赖性下的高斯近似。

英文摘要

We develop Gaussian approximation bounds in higher-order Wasserstein distance $W_p$, $p\geq2$, for sums of multivariate martingale differences generated by a uniformly ergodic Markov chain. Under an $L^{(2+η)p}$-moment condition with $η>0$, we establish the explicit bound $$ O\left( p^3 \|A\|_4^2 + pd^{1/4}\|A\|_2^{1/2}\|A\|_4^2 \right) $$ where $A\in\mathbb{R}^n$ collects the $L^{(2+η)p}$-sizes of the $n$ individual martingale increments. In the balanced-increment regime where the individual increments have comparable sizes of order $n^{-1/2}$, it yields the first optimal $O(n^{-1/2})$ Gaussian approximation rate for fixed $p$ and $d$. Consequently, we also obtain the first optimal $O(n^{-1/2})$ $W_p$ Gaussian approximation rate for multivariate additive functionals of uniformly ergodic Markov chains. Our analysis develops two techniques for addressing the interplay between higher-order Wasserstein distance and temporal dependence. First, building on the Ornstein--Uhlenbeck relative-score approach of Fang and Koike (2023), we formulate the bound in terms of antisymmetric Stein couplings while retaining the conditional tensor structure. Second, we develop a refresh-then-maximal coupling that combines an independent first-step resampling, which preserves the desired Stein identity, with a subsequent maximal coupling that provides effective control of the coupling increment. These tools may be useful more broadly for Gaussian approximation under temporal dependence.

发表机构

  • University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑