Blake Bordelon

Transfer Learning in Infinite Width Feature Learning Networks

Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time

$\mu$P for RL: Mitigating Feature Inconsistencies During Reinforcement Learning

Scaling Laws for Precision

Don't be lazy: CompleteP enables compute-efficient deep transformers

How Feature Learning Can Improve Neural Scaling Laws

Adaptive kernel predictors from feature-learning infinite limits of neural networks

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer

A Model of Place Field Reorganization During Reward Maximization

A Model of Place Field Reorganization During Reward Maximization