arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.10085cs.LGcs.AI
收藏

一种用于最优传输的基础度量学习的黎曼方法

A Riemannian Approach to Ground Metric Learning for Optimal Transport

Microsoft India(微软印度公司);The University of Sydney(悉尼大学)

Pratik Jawanpuria, Dai Shi, Bamdev Mishra, Junbin Gao

AI总结:

该研究针对最优传输中嵌入空间基础度量的关键影响问题,提出利用对称正定矩阵的黎曼几何结构,联合学习OT距离与由该矩阵参数化的潜在基础度量,验证了其在域适应任务中的有效性。

摘要:

最优传输(OT)理论在机器学习与信号处理应用中已受到广泛关注,它定义了源数据点与目标数据点的概率分布之间的距离概念。影响基于OT的距离的一个关键因素是源、目标数据点所在嵌入空间的基础度量。本研究提出学习一种由对称正定矩阵参数化的合适潜在基础度量,借助对称正定矩阵丰富的黎曼几何结构,将OT距离与基础度量进行联合学习。实验结果表明,所学习的度量在基于OT的域适应任务中具备有效性。

英文摘要:

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 points. A crucial factor that influences OT-based distances is the ground metric of the embedding space in which the source and target data points lie. In this work, we propose to learn a suitable latent ground metric parameterized by a symmetric positive definite matrix. We use the rich Riemannian geometry of symmetric positive definite matrices to jointly learn the OT distance along with the ground metric. Empirical results illustrate the efficacy of the learned metric in OT-based domain adaptation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑