5 papers
Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
Clarissa Lauditi, Cengiz Pehlevan, Blake Bordelon
We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mean-field theory (DMFT) that joi…
Generalization performance of narrow one-hidden layer networks in the teacher-student setting
Rodrigo Pérez Ortiz, Gibbs Nwemadji, Jean Barbier +4
Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-s…
Transfer Learning in Infinite Width Feature Learning Networks
Clarissa Lauditi, Blake Bordelon, Cengiz Pehlevan
We develop a theory of transfer learning in infinitely wide neural networks under gradient flow that quantifies when pretraining on a source task improves generalization on a targe…
Adaptive kernel predictors from feature-learning infinite limits of neural networks
Clarissa Lauditi, Blake Bordelon, Cengiz Pehlevan
Previous influential work showed that infinite width limits of neural networks in the lazy training regime are described by kernel machines. Here, we show that neural networks trai…
Impact of dendritic non-linearities on the computational capabilities of neurons
Clarissa Lauditi, Enrico M. Malatesta, Fabrizio Pittorino +3
How neurons integrate the myriad synaptic inputs scattered across their dendrites is a fundamental question in neuroscience. Multiple neurophysiological experiments have shown that…