3 papers
cond-mat.dis-nn2026
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…
cond-mat.dis-nn2026
The dimensionality of the Hopfield model
Cristopher Erazo, Santiago Acevedo, Alessandro Ingrosso
We use the Binary Intrinsic Dimension (BID), a geometrical measure designed for binary data, to analyze the Hopfield model, a paradigmatic spin system from statistical mechanics, m…
stat.ML2025
Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers
Federico Bassetti, Marco Gherardi, Alessandro Ingrosso +2
Deep linear networks have been extensively studied, as they provide simplified models of deep learning. However, little is known in the case of finite-width architectures with mult…