A General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes
arXiv:2610.28864v1 Announce Type: new Abstract: A systematic understanding of the global structure of neural-network loss landscapes remains challenging due to their high dimensionality. Symmetries arising from network architectures and learning objectives provide a way to investigate aspects of th…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.LG
A General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes