31 citations · 62 across the 14 of their papers we have counts for
14 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…
Inferring effective interactions and task-related brain states from large-scale neural activity with Restricted Boltzmann Machines
Nicolas Béreux, Giovanni Catania, Aurélien Decelle +3
Large-scale electrophysiological recordings now enable the simultaneous monitoring of thousands of neurons across multiple brain regions, revealing structured variability in popula…
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…
Effectiveness of probabilistic contact tracing in epidemic containment: the role of super-spreaders and transmission path reconstruction
A. P. Muntoni, F. Mazza, A. Braunstein +2
The recent COVID-19 pandemic underscores the significance of early-stage non-pharmacological intervention strategies. The widespread use of masks and the systematic implementation…
The Copycat Perceptron: Smashing Barriers Through Collective Learning
Giovanni Catania, Aurélien Decelle, Beatriz Seoane
We characterize the equilibrium properties of a model of coupled binary perceptrons in the teacher-student scenario, subject to a suitable cost function, with an explicit ferro…
Small-Coupling Dynamic Cavity: a Bayesian mean-field framework for epidemic inference
Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta +3
We present the Small-Coupling Dynamic Cavity (SCDC) method, a novel generalized mean-field approximation for epidemic inference and risk assessment within a fully Bayesian framewor…
Explaining the effects of non-convergent sampling in the training of Energy-Based Models
Elisabeth Agoritsas, Giovanni Catania, Aurélien Decelle +1
In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-Based models (EBMs). In particular, we show analytically that EBMs trained with non-pers…
Thermodynamics of bidirectional associative memories
Adriano Barra, Giovanni Catania, Aurélien Decelle +1
In this paper we investigate the equilibrium properties of bidirectional associative memories (BAMs). Introduced by Kosko in 1988 as a generalization of the Hopfield model to a bip…
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…
A Density Consistency approach to the inverse Ising problem
Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta +1
We propose a novel approach to the inverse Ising problem which employs the recently introduced Density Consistency approximation (DC) to determine the model parameters (couplings a…
Epidemic mitigation by statistical inference from contact tracing data
Antoine Baker, Indaco Biazzo, Alfredo Braunstein +10
Contact-tracing is an essential tool in order to mitigate the impact of pandemic such as the COVID-19. In order to achieve efficient and scalable contact-tracing in real time, digi…
Loop corrections in spin models through density consistency
Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta
Computing marginal distributions of discrete or semidiscrete Markov random fields (MRFs) is a fundamental, generally intractable problem with a vast number of applications in virtu…