Computing equivariant matrices on homogeneous spaces for Geometric Deep Learning and Automorphic Lie Algebras

Abstract

We develop an elementary method to compute spaces of equivariant maps from a homogeneous space $G/H$ of a Lie group $G$ to a module of this group. The Lie group is not required to be compact. More generally, we study spaces of invariant sections in homogeneous vector bundles, and take a special interest in the case where the fibres are algebras. These latter cases have a natural global algebra structure. We classify these automorphic algebras for the case where the homogeneous space has compact stabilisers. This work has applications in the theoretical development of geometric deep learning and also in the theory of automorphic Lie algebras.

In this second version, the title is modified and two appendices are added, following the peer-review process

References in corpus (9)

• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Gauge Equivariant Convolutional Networks and the Icosahedral CNN
• Reduction Groups and Automorphic Lie Algebras
• Lorentz Group Equivariant Neural Network for Particle Physics
• Reductions of integrable equations. Dihedral group
• On the Classification of Automorphic Lie Algebras
• Higher dimensional Automorphic Lie Algebras
• Homogeneous vector bundles and $G$-equivariant convolutional neural networks
• A classification of automorphic Lie algebras on complex tori