当前位置: X-MOL 学术Probab Theory Relat Fields › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Stein’s method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
Probability Theory and Related Fields ( IF 2 ) Pub Date : 2020-08-07 , DOI: 10.1007/s00440-020-00989-4
Thomas Bonis

We use Stein's method to bound the Wasserstein distance of order $2$ between a measure $\nu$ and the Gaussian measure using a stochastic process $(X_t)_{t \geq 0}$ such that $X_t$ is drawn from $\nu$ for any $t > 0$. If the stochastic process $(X_t)_{t \geq 0}$ satisfies an additional exchangeability assumption, we show it can also be used to obtain bounds on Wasserstein distances of any order $p \geq 1$. Using our results, we provide optimal convergence rates for the multi-dimensional Central Limit Theorem in terms of Wasserstein distances of any order $p \geq 2$ under simple moment assumptions.

中文翻译:

应用于多变量中心极限定理的用于 Wasserstein 距离的正态逼近的 Stein 方法

我们使用 Stein 的方法使用随机过程 $(X_t)_{t \geq 0}$ 来限制测度 $\nu$ 和高斯测度之间 $2$ 阶的 Wasserstein 距离,使得 $X_t$ 是从 $\ nu$ 表示任何 $t > 0$。如果随机过程 $(X_t)_{t \geq 0}$ 满足额外的可交换性假设,我们证明它也可以用于获得任何阶 $p \geq 1$ 的 Wasserstein 距离的边界。使用我们的结果,我们根据简单矩假设下任何阶 $p\geq 2$ 的 Wasserstein 距离为多维中心极限定理提供最佳收敛率。
更新日期:2020-08-07
down
wechat
bug