Statistical distances, i.e., discrepancy measures between probability distributions, are ubiquitous in probability theory, statistics and machine learning. To combat the curse of dimensionality when estimating these distances from data, recent work has proposed smoothing out local irregularities in the measured distributions via convolution with a Gaussian kernel. Motivated by the scalability of the smooth framework to high dimensions, we conduct an in-depth study of the structural and statistical behavior of the Gaussian-smoothed $p$-Wasserstein distance $\mathsf{W}_p^{(\sigma)}$, for arbitrary $p\geq 1$. We start by showing that $\mathsf{W}_p^{(\sigma)}$ admits a metric structure that is topologically equivalent to classic $\mathsf{W}_p$ and is stable with respect to perturbations in $\sigma$. Moving to statistical questions, we explore the asymptotic properties of $\mathsf{W}_p^{(\sigma)}(\hat{\mu}_n,\mu)$, where $\hat{\mu}_n$ is the empirical distribution of $n$ i.i.d. samples from $\mu$. To that end, we prove that $\mathsf{W}_p^{(\sigma)}$ is controlled by a $p$th order smooth dual Sobolev norm $\mathsf{d}_p^{(\sigma)}$. Since $\mathsf{d}_p^{(\sigma)}(\hat{\mu}_n,\mu)$ coincides with the supremum of an empirical process indexed by Gaussian-smoothed Sobolev functions, it lends itself well to analysis via empirical process theory. We derive the limit distribution of $\sqrt{n}\mathsf{d}_p^{(\sigma)}(\hat{\mu}_n,\mu)$ in all dimensions $d$, when $\mu$ is sub-Gaussian. Through the aforementioned bound, this implies a parametric empirical convergence rate of $n^{-1/2}$ for $\mathsf{W}_p^{(\sigma)}$, contrasting the $n^{-1/d}$ rate for unsmoothed $\mathsf{W}_p$ when $d \geq 3$. As applications, we provide asymptotic guarantees for two-sample testing and minimum distance estimation. When $p=2$, we further show that $\mathsf{d}_2^{(\sigma)}$ can be expressed as a maximum mean discrepancy.
翻译:统计距离 (mum{mu{mu{mu{mu{mu{mu{mu{mu{mu{mu{mu{musyunial discription) 在概率理论、 统计和机器学习方面, 都无处不在。 在估算离数据距离时, 要克服维度的诅咒, 最近的工作建议通过与高斯内核的连接来平息测量分布中的当地违规现象。 我们受光滑框架可伸缩至高维范围的激励, 我们深入研究了高斯-moth分布的结构和统计行为的结构性和统计行为。 谈到统计问题, 我们探索了美元- math(m%%) 美元(musm_qu_ma_ma_$美元) 的统计特性, 也显示美元- musicial_ma_ma_max max max max max max max max max max max max max max max max max max max max max max max max max max max max max max max maxxx maxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx