35 citations · 67 across the 7 of their papers we have counts for
7 papers
Kernel shape renormalization explains output-output correlations in finite Bayesian one-hidden-layer networks
P. Baglioni, L. Giambagli, A. Vezzani +3
Finite-width one hidden layer networks with multiple neurons in the readout layer display non-trivial output-output correlations that vanish in the lazy-training infinite-width lim…
Statistical mechanics of transfer learning in fully-connected networks in the proportional limit
Alessandro Ingrosso, Rosalba Pacelli, Pietro Rotondo +1
Transfer learning (TL) is a well-established machine learning technique to boost the generalization performance on a specific (target) task using information gained from a related…
Predictive power of a Bayesian effective action for fully-connected one hidden layer neural networks in the proportional limit
P. Baglioni, R. Pacelli, R. Aiudi +4
We perform accurate numerical experiments with fully-connected (FC) one-hidden layer neural networks trained with a discretized Langevin dynamics on the MNIST and CIFAR10 datasets.…
Local Kernel Renormalization as a mechanism for feature learning in overparametrized Convolutional Neural Networks
R. Aiudi, R. Pacelli, A. Vezzani +2
Feature learning, or the ability of deep neural networks to automatically learn relevant features from raw data, underlies their exceptional capability to solve complex tasks. Howe…
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit
R. Pacelli, S. Ariosto, M. Pastore +3
Despite the practical success of deep neural networks, a comprehensive theoretical framework that can predict practically relevant scores, such as the test accuracy, from knowledge…
Universal mean field upper bound for the generalisation gap of deep neural networks
S. Ariosto, R. Pacelli, F. Ginelli +2
Modern deep neural networks (DNNs) represent a formidable challenge for theorists: according to the commonly accepted probabilistic framework that describes their performance, thes…
Learning through atypical "phase transitions" in overparameterized neural networks
Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta +3
Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient…