论文标题
关于熵最佳运输的样品复杂性
On the sample complexity of entropic optimal transport
论文作者
论文摘要
我们使用计算有效的插件估计器研究了高维度熵最佳传输的样品复杂性。我们通过建立无维度的参数速率来显着提高艺术的状态，以估计各种关注量，包括熵回归函数，这是对最佳运输图的自然类似物。作为应用程序，我们提出了一个基于熵最佳运输的转移学习的实用模型，并为非参数回归和分类建立了收敛的参数速率。
We study the sample complexity of entropic optimal transport in high dimensions using computationally efficient plug-in estimators. We significantly advance the state of the art by establishing dimension-free, parametric rates for estimating various quantities of interest, including the entropic regression function which is a natural analog to the optimal transport map. As an application, we propose a practical model for transfer learning based on entropic optimal transport and establish parametric rates of convergence for nonparametric regression and classification.
