BriefGPT.xyz
Sep, 2024
基于黎曼几何的最优传输中的基础度量学习
A Riemannian Approach to Ground Metric Learning for Optimal Transport
HTML
PDF
Pratik Jawanpuria, Dai Shi, Bamdev Mishra, Junbin Gao
TL;DR
本研究解决了最优传输(O.T.)理论在源数据和目标数据点概率分布之间定义距离时基础度量的不足。我们提出了一种通过对称正定矩阵参数化的适当潜在基础度量的学习方法，利用其黎曼几何特性共同学习O.T.距离和基础度量，实证结果表明所学度量在O.T.基础的领域适应中具有良好效果。
Abstract
Optimal Transport
(OT) theory has attracted much attention in
Machine Learning
and signal processing applications. OT defines a notion of distance between probability distributions of source and target data point
→