Persistent Homology for Labeled Datasets: Gromov-Hausdorff Stability and Generalized Landscapes

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fu, Yaoying, Lagoda, Evgeniya, Li, Shiying, Needham, Tom, Hoef, Lander Ver, Weiler, Morgan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908702129258496
author Fu, Yaoying
Lagoda, Evgeniya
Li, Shiying
Needham, Tom
Hoef, Lander Ver
Weiler, Morgan
author_facet Fu, Yaoying
Lagoda, Evgeniya
Li, Shiying
Needham, Tom
Hoef, Lander Ver
Weiler, Morgan
contents Techniques from metric geometry have become fundamental tools in modern mathematical data science, providing principled methods for comparing datasets modeled as finite metric spaces. Two of the central tools in this area are the Gromov-Hausdorff distance and persistent homology, both of which yield isometry-invariant notions of distance between datasets. However, these frameworks do not account for categorical labels, which are intrinsic to many real-world datasets, such as labeled images, pre-clustered data, and semantically segmented shapes. In this paper, we introduce a general framework for labeled metric spaces and develop new notions of Gromov-Hausdorff distance and persistent homology which are adapted to this setting. Our main result shows that our persistent homology construction is stable with respect to our novel notion of Gromov-Hausdorff distance, extending a classic result in topological data analysis. To facilitate computation, we also introduce a labeled version of persistence landscapes and show that the landscape map is Lipschitz.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Persistent Homology for Labeled Datasets: Gromov-Hausdorff Stability and Generalized Landscapes
Fu, Yaoying
Lagoda, Evgeniya
Li, Shiying
Needham, Tom
Hoef, Lander Ver
Weiler, Morgan
Algebraic Topology
Metric Geometry
Techniques from metric geometry have become fundamental tools in modern mathematical data science, providing principled methods for comparing datasets modeled as finite metric spaces. Two of the central tools in this area are the Gromov-Hausdorff distance and persistent homology, both of which yield isometry-invariant notions of distance between datasets. However, these frameworks do not account for categorical labels, which are intrinsic to many real-world datasets, such as labeled images, pre-clustered data, and semantically segmented shapes. In this paper, we introduce a general framework for labeled metric spaces and develop new notions of Gromov-Hausdorff distance and persistent homology which are adapted to this setting. Our main result shows that our persistent homology construction is stable with respect to our novel notion of Gromov-Hausdorff distance, extending a classic result in topological data analysis. To facilitate computation, we also introduce a labeled version of persistence landscapes and show that the landscape map is Lipschitz.
title Persistent Homology for Labeled Datasets: Gromov-Hausdorff Stability and Generalized Landscapes
topic Algebraic Topology
Metric Geometry
url https://arxiv.org/abs/2512.08794