Graded Representation Theory of Equivariant Neural Networks

arXiv:2609.25776 · math.RT, cs.LG · Submitted 2026-09-22 · Read on arXiv

math.RT, cs.LG

Submitted: 2026-09-22

Updated: 2026-09-22

Comments: 33 pages, comments welcome

Project page: https://maani.info

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Core — 21× in this paper · explained in 2 episodes
• Hilbert Space — 3× in this paper · explained in 2 episodes
• Activation Function — 2× in this paper · explained in 1 episode
• Hypergraph — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Approximation Bound — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes

Sources

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• A Characterization Theorem for Equivariant Networks with Point-wise Activations

Related papers

• What is Smoothness?