arXiv (All)
open access
A Spectral Renormalization-Group View of Learning
We study how the layers in deep neural networks (NNs) converge, using Wilsonian Renormalization-Group (RG) ideas to organize the spectral picture. During training, these layers often develop heavy-tailed power-law (PL) spectra, and the strongest checkpoints often appear near the PL exponent $α\appro
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Dropout Neural Network Training Viewed from a Percolation Perspective#1049720
- Collective Kernel EFT for Pre-activation ResNets#1488351
- Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking#1234286
- Early learning in large residual networks#1446828
- Scaling and Renormalization in Neural Networks: An Effective Renormalization-Group Description of Grokking#1467437
Record · ID 1536252
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive