New Paper Applies Renormalization-Group Ideas to Deep Learning
A new arXiv paper uses Wilsonian renormalization-group methods to study how layers in deep neural networks converge, organizing the analysis through a spectral picture.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv cs.LG
A Spectral Renormalization-Group View of Learning