研究人员开发了一种新方法来优化 Wasserstein 距离估计的计算统计运行时间。这种称为 Sample-Sketch-Solve 的技术使用规则的笛卡尔网格来草绘数据，在不增加渐近误差的情况下对其进行压缩。该方法能够实现更快的精确算法，并在特定平滑分布的最优时间复杂度内，以 epsilon 误差近似 Wasserstein-2 平方距离。 AI
影响 提高了机器学习模型评估中核心统计工具的效率。
排序理由 详细介绍新计算方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.20122v1 Announce Type: new Abstract: Squared Wasserstein distance is a frequently used tool to measure discrepancy between probability distributions. This distance is typically computed between empirical measures of size $n$ from two underlying random samples. Unfortun…
Squared Wasserstein distance is a frequently used tool to measure discrepancy between probability distributions. This distance is typically computed between empirical measures of size $n$ from two underlying random samples. Unfortunately, even in lower dimensional Euclidean space…