arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.08859cs.LG
收藏

数据集相似性的几何度量:幅度距离

Magnitude Distance: A Geometric Measure of Dataset Similarity

School of Informatics, University of Edinburgh(信息学院,爱丁堡大学)

Sahel Torkamani, Henry Gouk, Rik Sarkar

AI总结:

本文提出幅度距离作为衡量数据集相似性的几何度量,通过可调参数控制尺度敏感性,并在高维空间中保持判别能力,用于生成模型的训练目标。

摘要:

量化数据集之间的距离是数学和机器学习中的基本问题。我们提出了幅度距离,这是一种基于度量空间的幅度概念定义在有限数据集上的新距离度量。所提出的方法包含一个可调的缩放参数t,该参数控制对全局结构(小t)和细节(大t)的敏感性。我们证明了幅度距离的几个理论性质,包括其在不同尺度下的极限行为以及满足关键度量性质的条件。与经典距离不同,我们表明在适当调整尺度时,幅度距离在高维设置中仍能保持判别能力。我们进一步展示了如何将幅度距离用作推前生成模型的训练目标。我们的实验结果支持我们的理论分析,并表明幅度距离提供了有意义的信号,与已建立的距离基生成方法相当。

英文摘要:

Quantifying the distance between datasets is a fundamental question in mathematics and machine learning. We propose \textit{magnitude distance}, a novel distance metric defined on finite datasets using the notion of the \emph{magnitude} of a metric space. The proposed distance incorporates a tunable scaling parameter, $t$, that controls the sensitivity to global structure (small $t$) and finer details (large $t$). We prove several theoretical properties of magnitude distance, including its limiting behavior across scales and conditions under which it satisfies key metric properties. In contrast to classical distances, we show that magnitude distance remains discriminative in high-dimensional settings when the scale is appropriately tuned. We further demonstrate how magnitude distance can be used as a training objective for push-forward generative models. Our experimental results support our theoretical analysis and demonstrate that magnitude distance provides meaningful signals, comparable to established distance-based generative approaches.

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。

↑