arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.14860cs.LGstat.ML
收藏

时间非齐次扩散几何与拓扑

Time-inhomogeneous diffusion geometry and topology

Université de Montréal(蒙特利尔大学);Mila - Quebec AI Institute(Mila - 魁北克人工智能研究所);Helmholtz Munich(亥姆霍兹慕尼黑中心);Technical University of Munich(慕尼黑工业大学);Yale University(耶鲁大学);Michigan State University(密歇根州立大学)

Guillaume Huguet, Alexander Tong, Bastian Rieck, Jessie Huang, Manik Kuchroo, Matthew Hirn, Guy Wolf, Smita Krishnaswamy

摘要:

扩散凝聚是一个动态的过程,产生一系列的多尺度数据表示,旨在编码有意义的抽象。它已被证明是有效的流形学习,去噪,聚类和高维数据的可视化。扩散凝聚被构造为一个时间不均匀的过程,其中每一步首先计算,然后将扩散算子应用于数据。我们从几何、光谱和拓扑的角度理论上分析了这一过程的收敛和演化。从几何的角度来看,我们得到的最小转移概率和数据的半径的基础上的收敛边界,而从光谱的角度来看,我们的边界是基于本征谱的扩散内核。我们的谱结果是特别感兴趣的,因为大多数文献的数据扩散都集中在均匀的过程。从拓扑的角度来看,我们扩散凝聚推广基于质心的层次聚类。我们使用这种观点来获得一个边界的基础上的数据点的数量,独立于他们的位置。为了理解数据几何结构的演变超出收敛,我们使用拓扑数据分析。我们表明,缩合过程本身定义了一个内在的缩合同源性。我们使用这种内在的拓扑结构,以及周围的持续同源的凝聚过程中,研究如何随着扩散时间的数据变化。我们证明了这两种类型的拓扑信息在很好理解的玩具的例子。我们的工作提供了理论上的见解扩散凝聚的收敛性,并表明它提供了拓扑和几何数据分析之间的联系。

英文摘要:

Diffusion condensation is a dynamic process that yields a sequence of multiscale data representations that aim to encode meaningful abstractions. It has proven effective for manifold learning, denoising, clustering, and visualization of high-dimensional data. Diffusion condensation is constructed as a time-inhomogeneous process where each step first computes and then applies a diffusion operator to the data. We theoretically analyze the convergence and evolution of this process from geometric, spectral, and topological perspectives. From a geometric perspective, we obtain convergence bounds based on the smallest transition probability and the radius of the data, whereas from a spectral perspective, our bounds are based on the eigenspectrum of the diffusion kernel. Our spectral results are of particular interest since most of the literature on data diffusion is focused on homogeneous processes. From a topological perspective, we show diffusion condensation generalizes centroid-based hierarchical clustering. We use this perspective to obtain a bound based on the number of data points, independent of their location. To understand the evolution of the data geometry beyond convergence, we use topological data analysis. We show that the condensation process itself defines an intrinsic condensation homology. We use this intrinsic topology as well as the ambient persistent homology of the condensation process to study how the data changes over diffusion time. We demonstrate both types of topological information in well-understood toy examples. Our work gives theoretical insights into the convergence of diffusion condensation, and shows that it provides a link between topological and geometric 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。

↑