Erzeugunsgrad, VC-Dimension and Neural Networks with rational activation function

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pardo, Luis Miguel, Sebastián, Daniel
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915244081676288
author Pardo, Luis Miguel
Sebastián, Daniel
author_facet Pardo, Luis Miguel
Sebastián, Daniel
contents The notion of Erzeugungsgrad was introduced by Joos Heintz in 1983 to bound the number of non-empty cells occurring after a process of quantifier elimination. We extend this notion and the combinatorial bounds of Theorem 2 in Heintz (1983) using the degree for constructible sets defined in Pardo-Sebastián (2022). We show that the Erzeugungsgrad is the key ingredient to connect affine Intersection Theory over algebraically closed fields and the VC-Theory of Computational Learning Theory for families of classifiers given by parameterized families of constructible sets. In particular, we prove that the VC-dimension and the Krull dimension are linearly related up to logarithmic factors based on Intersection Theory. Using this relation, we study the density of correct test sequences in evasive varieties. We apply these ideas to analyze parameterized families of neural networks with rational activation function.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11345
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Erzeugunsgrad, VC-Dimension and Neural Networks with rational activation function
Pardo, Luis Miguel
Sebastián, Daniel
Machine Learning
Algebraic Geometry
13F20, 14A10, 68T07
The notion of Erzeugungsgrad was introduced by Joos Heintz in 1983 to bound the number of non-empty cells occurring after a process of quantifier elimination. We extend this notion and the combinatorial bounds of Theorem 2 in Heintz (1983) using the degree for constructible sets defined in Pardo-Sebastián (2022). We show that the Erzeugungsgrad is the key ingredient to connect affine Intersection Theory over algebraically closed fields and the VC-Theory of Computational Learning Theory for families of classifiers given by parameterized families of constructible sets. In particular, we prove that the VC-dimension and the Krull dimension are linearly related up to logarithmic factors based on Intersection Theory. Using this relation, we study the density of correct test sequences in evasive varieties. We apply these ideas to analyze parameterized families of neural networks with rational activation function.
title Erzeugunsgrad, VC-Dimension and Neural Networks with rational activation function
topic Machine Learning
Algebraic Geometry
13F20, 14A10, 68T07
url https://arxiv.org/abs/2504.11345