The Geometry of Polynomial Group Convolutional Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917373255090176 |
|---|---|
| author | Hendi, Yacoub Persson, Daniel Larfors, Magdalena |
| author_facet | Hendi, Yacoub Persson, Daniel Larfors, Magdalena |
| contents | We study polynomial group convolutional neural networks (PGCNNs) for an arbitrary finite group $G$. In particular, we introduce a new mathematical framework for PGCNNs using the language of graded group algebras. This framework yields two natural parametrizations of the architecture, based on Hadamard and Kronecker products, related by a linear map. We compute the dimension of the associated neuromanifold, verifying that it depends only on the number of layers and the size of the group. We also describe the general fiber of the Kronecker parametrization up to the regular group action and rescaling, and conjecture the analogous description for the Hadamard parametrization. Our conjecture is supported by explicit computations for small groups and shallow networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29566 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Geometry of Polynomial Group Convolutional Neural Networks Hendi, Yacoub Persson, Daniel Larfors, Magdalena Machine Learning Algebraic Geometry We study polynomial group convolutional neural networks (PGCNNs) for an arbitrary finite group $G$. In particular, we introduce a new mathematical framework for PGCNNs using the language of graded group algebras. This framework yields two natural parametrizations of the architecture, based on Hadamard and Kronecker products, related by a linear map. We compute the dimension of the associated neuromanifold, verifying that it depends only on the number of layers and the size of the group. We also describe the general fiber of the Kronecker parametrization up to the regular group action and rescaling, and conjecture the analogous description for the Hadamard parametrization. Our conjecture is supported by explicit computations for small groups and shallow networks. |
| title | The Geometry of Polynomial Group Convolutional Neural Networks |
| topic | Machine Learning Algebraic Geometry |
| url | https://arxiv.org/abs/2603.29566 |