Skip to contentSkip to filters

We use cookies for analytics.

Generalization and overfitting in two-layer neural networks

Recording

59 min

Abstract

Implicit bias, benign overfitting, and the emergence of useful features can depend on how an overparameterized network changes during training. Using dynamical mean-field theory from statistical physics, the speaker analyzes nonlinear training dynamics in large two-layer networks and examines when generalization and overfitting arise.

Topics