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 2202.10723cs.LGcs.AIstat.ML
收藏

Sobolev迁移:一个基于图的概率测度的可伸缩度量

Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics

RIKEN AIP(理化学研究所先进智能项目中心);The University of Akron(阿克伦大学);Monash University(莫纳什大学);VinAI Research(VinAI研究院)

Tam Le, Truyen Nguyen, Dinh Phung, Viet Anh Nguyen

摘要:

最优运输(OT)是比较概率分布的一种常用方法。然而,OT具有一些缺点,如(i)计算复杂度高,(ii)不确定性,这限制了其适用于内核机器。在这项工作中,我们认为概率措施支持图度量空间,并提出了一种新的Sobolev运输度量。我们证明了Sobolev输运度规给出了一个用于快速计算的封闭公式,并且它是负定的。我们证明了赋予这种传输距离的概率测度空间是等距于欧氏空间中具有加权$\ell_p$距离的有界凸集。我们进一步利用Sobolev运输的负定性设计正定内核,并评估其性能对其他基线的文档分类与词嵌入和拓扑数据分析。

英文摘要:

Optimal transport (OT) is a popular measure to compare probability distributions. However, OT suffers a few drawbacks such as (i) a high complexity for computation, (ii) indefiniteness which limits its applicability to kernel machines. In this work, we consider probability measures supported on a graph metric space and propose a novel Sobolev transport metric. We show that the Sobolev transport metric yields a closed-form formula for fast computation and it is negative definite. We show that the space of probability measures endowed with this transport distance is isometric to a bounded convex set in a Euclidean space with a weighted $\ell_p$ distance. We further exploit the negative definiteness of the Sobolev transport to design positive-definite kernels, and evaluate their performances against other baselines in document classification with word embeddings and in topological data analysis.

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。

↑