Blake Bordelon

9

Papers

108

Total Citations

Papers (9)

Grokking as the transition from lazy to rich training dynamics

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit

A Dynamical Model of Neural Scaling Laws

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks

Loss Dynamics of Temporal Difference Reinforcement Learning

Out-of-Distribution Generalization in Kernel Regression

Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales