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 2407.09297cs.LGstat.ML
收藏

使用归一化流和分数匹配从数据中学习距离

Learning Distances from Data with Normalizing Flows and Score Matching

Heidelberg University(海德堡大学)

Peter Sorrenson, Daniel Behrend-Uriarte, Christoph Schnörr, Ullrich Köthe

AI总结:

本文提出使用归一化流学习密度并结合分数模型引导的松弛方法优化测地线,同时引入维度自适应Fermat距离,解决了高维空间中基于密度的距离估计收敛差和扩展性不足的问题。

摘要:

基于密度的距离(DBDs)通过基于底层数据分布定义距离,为度量学习提供了一种有原则的方法。通过采用在低概率密度区域增加的黎曼度量,最短路径自然地遵循数据流形。Fermat距离作为DBD的一种特定类型,具有吸引人的特性,但基于最近邻图的现有估计器由于密度估计不准确而收敛性差。此外,基于图的方法在高维空间中扩展性差,因为所提出的测地线通常不够平滑。我们通过两种关键方式应对这些挑战。首先,我们使用归一化流学习密度。其次,我们通过松弛来细化测地线,并由学习的分数模型引导。此外,我们引入了一种维度自适应的Fermat距离,它能直观地扩展到高维空间并提高数值稳定性。我们的工作为基于密度的距离的实际应用铺平了道路,尤其是在高维空间中。

英文摘要:

Density-based distances (DBDs) provide a principled approach to metric learning by defining distances in terms of the underlying data distribution. By employing a Riemannian metric that increases in regions of low probability density, shortest paths naturally follow the data manifold. Fermat distances, a specific type of DBD, have attractive properties, but existing estimators based on nearest neighbor graphs suffer from poor convergence due to inaccurate density estimates. Moreover, graph-based methods scale poorly to high dimensions, as the proposed geodesics are often insufficiently smooth. We address these challenges in two key ways. First, we learn densities using normalizing flows. Second, we refine geodesics through relaxation, guided by a learned score model. Additionally, we introduce a dimension-adapted Fermat distance that scales intuitively to high dimensions and improves numerical stability. Our work paves the way for the practical use of density-based distances, especially in high-dimensional spaces.

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。

↑