 Bayes-optimal Learning of Deep Random Networks of Extensive-widthInternational Conference on Machine Learning (ICML), 2023 |
 Neural networks trained with SGD learn distributions of increasing
complexityInternational Conference on Machine Learning (ICML), 2022 |
 Separation of Scales and a Thermodynamic Description of Feature Learning
in Some CNNsNature Communications (Nat Commun), 2021 |
