Fiber Bundle Learning: A Topological Framework for Classification Using Homology and Discrete Connections
International Journal of Topology · 17.06.2026 · 3 (2) · 12
DOI: 10.3390/ijt3020012 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Topology, online erschienen am 17.06.2026. Verfasst von Arturo Tozzi. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Many machine-learning tasks involve structured data whose geometry, local feature distributions, and global organization interact in ways that are not well captured by existing methods based on vectorization, graph metrics, or homological signatures. We introduce Fiber Bundle Learning (FBL), a topological framework that represents each data sample as a discrete fiber bundle and extracts a classification signature combining persistent homology, local feature geometry, and gluing structure. FBL builds a base space from the coarse geometry of each object, models local feature patches as fibers, and estimates transition maps between neighboring fibers to construct a discrete connection. From this representation, FBL computes a set of invariants: persistent homology of the base, fibers, and total space; holonomy obtained by transporting fiber states along cycles; curvature-like quantities measuring transition inconsistency; and discrete analogues of characteristic classes. These components are assembled into a fixed-length feature vector that can be used with any standard classifier. We show that FBL yields a signature with three desirable theoretical properties: stability under perturbations of geometry and local features, invariance under isometries and global fiber reparameterizations, and robustness to sampling noise. Our synthetic experiments show that FBL distinguishes twisted from untwisted bundles with identical homology, a distinction classical topological methods fail to capture. Additional tests quantify the system’s resistance to noise, its invariance to geometric transformations, and the contribution of each signature component. Taken together, our results indicate that representing data through fiber bundle structure may provide an effective tool for classifying complex, multi-level objects.
Zitieren
APA
Tozzi, A. (2026). Fiber Bundle Learning: A Topological Framework for Classification Using Homology and Discrete Connections. International Journal of Topology, 3(2), 12. https://doi.org/10.3390/ijt3020012
Vancouver
Tozzi A. Fiber Bundle Learning: A Topological Framework for Classification Using Homology and Discrete Connections. International Journal of Topology. 2026;3(2):12. doi:10.3390/ijt3020012
BibTeX
@article{Tozzi2026,
author = {Tozzi, Arturo},
title = {Fiber Bundle Learning: A Topological Framework for Classification Using Homology and Discrete Connections},
journal = {International Journal of Topology},
year = {2026},
volume = {3},
number = {2},
pages = {12},
doi = {10.3390/ijt3020012}
}
EUVIMED