arXiv stat.ML
· Papers
Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
arXiv:2401.04013v3 Announce Type: replace-cross Abstract: Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of interacting degrees of freedom. Such systems in the infinite limit, tend to exhibit simplified dynamics. This paper