A General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes
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 this structure.
By Jingzhou LiuarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 22, 2026.
Comments
Sign in to join the discussion.