Cover Learning for Large-Scale Topology Representation.

First Authors Luis Scoccola
Authors Luis Scoccola, Uzu Lim, Heather A Harrington
Corresponding Authors Luis Scoccola
Last Authors Heather A Harrington
Conference Proceedings Volume Title Proceedings of the 42nd International Conference on Machine Learning
Series Title (Proceedings of Machine Learning Research ; 267)
Conference Name 42nd International Conference on Machine Learning - ICML-Annual
Conference Location Vancouver, CANADA
Conference Start Date 2025-06-13
Conference End Date 2025-06-19
Chapter Number
Publisher JMLR-Journal Machine Learning Research
Conference Proceedings Editors
ISBN
First Page 53728
Last Page 53756
Open Access true
Print Publication Date 2025-06-19
Online Publication Date 2025-06-19
Abstract Classical unsupervised learning methods like clustering and linear dimensionality reduction parametrize large-scale geometry when it is discrete or linear, while more modern methods from manifold learning find low dimensional representation or infer local geometry by constructing a graph on the input data. More recently, topological data analysis popularized the use of simplicial complexes to represent data topology with two main methodologies: topological inference with geometric complexes and large-scale topology visualization with Mapper graphs - central to these is the nerve construction from topology, which builds a simplicial complex given a cover of a space by subsets. While successful, these have limitations: geometric complexes scale poorly with data size, and Mapper graphs can be hard to tune and only contain low dimensional information. In this paper, we propose to study the problem of learning covers in its own right, and from the perspective of optimization. We describe a method for learning topologically-faithful covers of geometric datasets, and show that the simplicial complexes thus obtained can outperform standard topological inference approaches in terms of size, and Mapper-type algorithms in terms of representation of large-scale topology.
Cover Image
Affiliated With CSBD, Harrington
Selected By
Acknowledged Services
Publication Status Published
Edoc Link
Sfx Link
DOI
PubMed ID
WebOfScience Link WOS:001693164800033
Alternative Full Text URL https://proceedings.mlr.press/v267/
Display Publisher Download Only false
Visible On MPI-CBG Website true
PDF Downloadable true
Created By thuem
Added Date 2026-04-16
Last Edited By thuem
Last Edited Date 2026-04-24 13:38:18.9
Library ID 9207
Document ID
Entry Complete true
eDoc Compliant true
Include in Edoc Report true
In Pure false
Ready for eDoc Export false
Author Affiliations Complete false
Project Name
Project URL
Grant ID
Funding Programme
Funding Organisation