papers

Publications (7)

cond-mat.dis-nn2024

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.…

cs.LG2023

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…

cond-mat.dis-nn2022

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…

cond-mat.dis-nn2024

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…

cond-mat.stat-mech2020

Singularities in large deviations of work in quantum quenches

P. Rotondo, J. Minar, J. P. Garrahan +2

We investigate large deviations of the work performed in a quantum quench across two different phases separated by a quantum critical point, using as example the Dicke model quench…

cond-mat.dis-nn2023

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…