Torsion in Persistent Homology and Neural Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Walch, Maria
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909797786320896
author Walch, Maria
author_facet Walch, Maria
contents We explore the role of torsion in hybrid deep learning models that incorporate topological data analysis, focusing on autoencoders. While most TDA tools use field coefficients, this conceals torsional features present in integer homology. We show that torsion can be lost during encoding, altered in the latent space, and in many cases, not reconstructed by standard decoders. Using both synthetic and high-dimensional data, we evaluate torsion sensitivity to perturbations and assess its recoverability across several autoencoder architectures. Our findings reveal key limitations of field-based approaches and underline the need for architectures or loss terms that preserve torsional information for robust data representation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Torsion in Persistent Homology and Neural Networks
Walch, Maria
Algebraic Topology
Machine Learning
We explore the role of torsion in hybrid deep learning models that incorporate topological data analysis, focusing on autoencoders. While most TDA tools use field coefficients, this conceals torsional features present in integer homology. We show that torsion can be lost during encoding, altered in the latent space, and in many cases, not reconstructed by standard decoders. Using both synthetic and high-dimensional data, we evaluate torsion sensitivity to perturbations and assess its recoverability across several autoencoder architectures. Our findings reveal key limitations of field-based approaches and underline the need for architectures or loss terms that preserve torsional information for robust data representation.
title Torsion in Persistent Homology and Neural Networks
topic Algebraic Topology
Machine Learning
url https://arxiv.org/abs/2506.03049