7 papers
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…
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…
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…
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…
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…
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…