collaborators

7 papers

cond-mat.dis-nn2026

A solvable model for unsupervised federated learning

Giovanni Catania, Aurélien Decelle, Gianluca Manzan +2

We introduce a theoretical framework for analyzing federated learning in a generative setting through a teacher-multiple interacting students scenario, in which each student receiv…

cond-mat.dis-nn2026

The Symmetric Perceptron: a Teacher-Student Scenario

Giovanni Catania, Aurélien Decelle, Suhanee Korpe

We introduce and solve a teacher-student formulation of the symmetric binary Perceptron, turning a traditionally storage-oriented model into a planted inference problem with a guar…

q-bio.NC2026

Uncovering statistical structure in large-scale neural activity with Restricted Boltzmann Machines

Nicolas Béreux, Giovanni Catania, Aurélien Decelle +3

Large-scale electrophysiological recordings now allow simultaneous monitoring of thousands of neurons across multiple brain regions, revealing structured variability in neural popu…

physics.data-an2026

Inference in conditioned dynamics through causality restoration

Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta +2

Computing observables from conditioned dynamics is typically computationally hard, because, although obtaining independent samples efficiently from the unconditioned dynamics is us…

cond-mat.dis-nn2025

On the role of non-linear latent features in bipartite generative neural networks

Tony Bonnaire, Giovanni Catania, Aurélien Decelle +1

We investigate the phase diagram and memory retrieval capabilities of bipartite energy-based neural networks, namely Restricted Boltzmann Machines (RBMs), as a function of the prio…

cs.LG2025

A theoretical framework for overfitting in energy-based modeling

Giovanni Catania, Aurélien Decelle, Cyril Furtlehner +1

We investigate the impact of limited data on training pairwise energy-based models for inverse problems aimed at identifying interaction networks. Utilizing the Gaussian model as t…