Arthur Jacot

Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

Shallow diffusion networks provably learn hidden low-dimensional structure

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets