AI RESEARCH
Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency
arXiv CS.LG
•
ArXi:2406.07598v5 Announce Type: replace We consider achieving equivariance in machine learning systems via frame averaging. Current frame averaging methods involve a costly sum over large frames or rely on sampling-based approaches that only yield approximate equivariance. Here, we propose Minimal Frame Averaging (MFA), a mathematical framework for constructing provably minimal frames that are exactly equivariant.