AINeutralarXiv – CS AI · 3h ago6/10
🧠
How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
Researchers demonstrate that the Muon optimizer significantly outperforms Adam when training equivariant neural networks, which encode geometric symmetries by design. Analysis of trained models reveals Muon produces solutions with more regular loss surfaces, higher weight ranks, and better-conditioned representations, suggesting optimizer choice substantially influences how neural networks learn geometric constraints.