1 citations · 1 across the 2 of their papers we have counts for
3 papers
A Caveat on Metrizing Convergence in Distribution on Hilbert Spaces
Federico Bassetti, Solesne Bourguin, Simon Campese +1
We consider Sobolev-type distances on probability measures over separable Hilbert spaces involving the Schatten- norms, which include as special cases a distance first introduce…
Proportional infinite-width infinite-depth limit for deep linear neural networks
Federico Bassetti, Lucia Ladelli, Pietro Rotondo
We study the distributional properties of linear neural networks with random parameters in the context of large networks, where the number of layers diverges in proportion to the n…
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…