We provide some non asymptotic bounds, with explicit constants, that measure the rate of convergence, in expected Wasserstein distance, of the empirical measure associated to an i.i.d. $N$-sample of a given probability distribution on $\mathbb{R}^d$. We consider the cases where $\mathbb{R}^d$ is endowed with the maximum and Euclidean norms.
翻译:我们提供一些非无药可治的界限,并配有明确的常数,用以衡量与一一一一一(a)d.美元(mathbb{R ⁇ d$)的某一概率分布样本有关的实证措施在预期的瓦森斯坦距离方面的趋同率。我们考虑了美元(mathbb{R ⁇ d$)具有最高和欧几里德规范的情况。