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 2303.08456cs.CGmath.STstat.MLstat.TH
收藏

基于度量的统计学习:一个应用于持续图的实例

Statistical learning on measures: an application to persistence diagrams

Kyoto University(京都大学)

Olympio Hacquard, Gilles Blanchard, Clément Levrard

AI总结:

本文提出了一种基于度量的统计学习方法,应用于持续图的分类问题,通过拓扑描述符实现高效的分类性能。

摘要:

我们考虑一个二分类监督学习问题,其中数据不是在有限维欧几里得空间中,而是观察到在紧空间X上的度量。形式上,我们观察到数据D_N=(μ_1,Y_1),...,,(μ_N,Y_N),其中μ_i是X上的度量,Y_i是{0,1}中的标签。给定一个基分类器集合F在X上,我们构建对应的度量空间中的分类器。我们提供了该新分类器类的Rademacher复杂度的上界和下界,这些复杂度可以简单地用相应类F的复杂度来表示。如果度量μ_i在有限集上是均匀的,这种分类任务就转化为多实例学习问题。然而,我们的方法允许更灵活和多样化的输入数据。尽管这种框架有许多可能的应用,本工作强调通过称为持续图的拓扑描述符进行分类。这些对象是R²上的离散度量,每个点的坐标对应于拓扑特征存在的尺度范围。我们将展示几种度量上的分类器,并展示它们如何在持续图的各种情况下通过启发式和理论方法实现良好的分类性能。

英文摘要:

We consider a binary supervised learning classification problem where instead of having data in a finite-dimensional Euclidean space, we observe measures on a compact space $\mathcal{X}$. Formally, we observe data $D_N = (μ_1, Y_1), \ldots, (μ_N, Y_N)$ where $μ_i$ is a measure on $\mathcal{X}$ and $Y_i$ is a label in $\{0, 1\}$. Given a set $\mathcal{F}$ of base-classifiers on $\mathcal{X}$, we build corresponding classifiers in the space of measures. We provide upper and lower bounds on the Rademacher complexity of this new class of classifiers that can be expressed simply in terms of corresponding quantities for the class $\mathcal{F}$. If the measures $μ_i$ are uniform over a finite set, this classification task boils down to a multi-instance learning problem. However, our approach allows more flexibility and diversity in the input data we can deal with. While such a framework has many possible applications, this work strongly emphasizes on classifying data via topological descriptors called persistence diagrams. These objects are discrete measures on $\mathbb{R}^2$, where the coordinates of each point correspond to the range of scales at which a topological feature exists. We will present several classifiers on measures and show how they can heuristically and theoretically enable a good classification performance in various settings in the case of persistence diagrams.

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。

↑