Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: García-Castellanos, Alejandro, Bellaard, Gijs, Duits, Remco, Pelt, Daniel, Bekkers, Erik J
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918380596887552
author García-Castellanos, Alejandro
Bellaard, Gijs
Duits, Remco
Pelt, Daniel
Bekkers, Erik J
author_facet García-Castellanos, Alejandro
Bellaard, Gijs
Duits, Remco
Pelt, Daniel
Bekkers, Erik J
contents Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying different group actions, where standard techniques do not directly apply. We show that, when a group $G$ acts transitively on a space $M$, any $G$-invariant function on a product space $X \times M$ can be reduced to an invariant of the isotropy subgroup $H$ of $M$ acting on $X$ alone. Our approach establishes an explicit orbit equivalence $(X \times M)/G \cong X/H$, yielding a principled reduction that preserves expressivity. We apply this characterization to Equivariant Neural Fields, extending them to arbitrary group actions and homogeneous conditioning spaces, and thereby removing the major structural constraints imposed by existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08758
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
García-Castellanos, Alejandro
Bellaard, Gijs
Duits, Remco
Pelt, Daniel
Bekkers, Erik J
Machine Learning
Artificial Intelligence
Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying different group actions, where standard techniques do not directly apply. We show that, when a group $G$ acts transitively on a space $M$, any $G$-invariant function on a product space $X \times M$ can be reduced to an invariant of the isotropy subgroup $H$ of $M$ acting on $X$ alone. Our approach establishes an explicit orbit equivalence $(X \times M)/G \cong X/H$, yielding a principled reduction that preserves expressivity. We apply this characterization to Equivariant Neural Fields, extending them to arbitrary group actions and homogeneous conditioning spaces, and thereby removing the major structural constraints imposed by existing methods.
title Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.08758