dynamical mean field theory
PulseAugur coverage of dynamical mean field theory — every cluster mentioning dynamical mean field theory across labs, papers, and developer communities, ranked by signal.
-
New research analyzes neural network training dynamics in high dimensions
A new research paper published on arXiv analyzes the high-dimensional training dynamics of shallow neural networks with quadratic activation functions. The study focuses on the extensive-width regime, where network widt…
-
Machine learning generalization linked to superconducting transition physics
Researchers have utilized dynamical mean field theory to explain the phenomenon of "double descent" in machine learning, where generalization improves even when model capacity exceeds data points. This behavior is ident…
-
Machine learning double descent linked to superconducting transition physics
A new paper explores the phenomenon of "double descent" in machine learning, where neural networks continue to improve their generalization capabilities even as their complexity surpasses the amount of training data. Re…
-
Dynamical Mean Field Theory Explains AI Feature Learning
Pierfrancesco Urbani presented research on applying dynamical mean field theory to analyze feature learning and overfitting in large neural networks. The talk, held at the Harvard Center of Mathematical Sciences and App…
-
New theories explore spectral dynamics in deep neural network training
Two new arXiv papers explore the spectral dynamics of deep neural networks during training. One paper introduces "Neural Low-Degree Filtering" (Neural LoFi) as a theoretical framework to understand hierarchical feature …