Piecewise Linear Equivariant Maps for Compact Groups
Not on the map. Why?
Abstract (arXiv)
Motivated by equivariant neural networks, we study piecewise linear equivariant maps between finite-dimensional real representations of compact groups. We show that all genuinely non-linear piecewise linear behaviour is confined to the subspaces on which the identity component of the group acts trivially, while equivariance forces linearity on the corresponding orthogonal complements. As a consequence, we obtain a compact-group analogue of the finite-group existence criterion of Gibson--Tubbenhauer--Williamson for non-zero equivariant piecewise linear maps between irreducible representations, with the identity component giving rise to a rigidity phenomenon absent from the finite-group case.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 5 of its 11 references that are in the map. First posted on arXiv 21 Aug 2026.
Builds on
5 of 11 references.
References · 5
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 739
- 2022Functional dimension of feedforward ReLU neural networkscited by 20
- 2024A Characterization Theorem for Equivariant Networks with Point-wise Activationscited by 9
- 2024Neural reproducing kernel Banach spaces and representer theorems for deep networkscited by 8
- 2024Equivariant neural networks and piecewise linear representation theorycited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026Graded Representation Theory of Equivariant Neural Networks22 Sep 2026