collaborators

9 papers

cs.LG2026

Variational Bounds for Perceptron Learning from Structured Data

Francesco Camilli, Pierluigi Contucci, Federica Gerace +1

We introduce a variational approach to a finite-temperature continuous-spin perceptron trained on a Gaussian mixture. The model allows for a broad class of concave utilities and lo…

math-ph2026

On the phase diagram of the multiscale mean-field spin-glass

Francesco Camilli, Pierluigi Contucci, Emanuele Mingione +1

In this paper we study the phase diagram of a Sherrington-Kirkpatrick (SK) model where the couplings are forced to thermalize at different time scales. Besides being a challenging…

math-ph2025

From entropic constraints to reinforced processes: a probabilistic origin of multiscale measures

Francesco Camilli, Pierluigi Contucci, Emanuele Mingione

We investigate multiscale Gibbs measures from a variational and probabilistic viewpoint, focusing on the structural asymmetry among conditional entropies that characterizes their c…

stat.ML2025

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation

Jean Barbier, Francesco Camilli, Minh-Toan Nguyen +2

For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capacity to tackle deep learning models cap…

stat.ML2025

Statistical mechanics of extensive-width Bayesian neural networks near interpolation

Jean Barbier, Francesco Camilli, Minh-Toan Nguyen +2

For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features m…

math.ST2025

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime

Francesco Camilli, Daria Tieplova, Eleonora Bergamin +1

We rigorously analyse fully-trained neural networks of arbitrary depth in the Bayesian optimal setting in the so-called proportional scaling regime where the number of training sam…