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 $\mathbb{R}^d$.
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i.d.d.有关的实证措施在预期的瓦森斯坦距离方面的趋同率,即以美元为单位的某一概率分布的样本,按美元=mathbb{R<unk> d$计算。</s>