collaborators

5 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 effect of priors on Learning with Restricted Boltzmann Machines

Gianluca Manzan, Daniele Tantari

Restricted Boltzmann Machines (RBMs) are generative models designed to learn from data with a rich underlying structure. In this work, we explore a teacher-student setting where a…

cs.LG2026

Saddle Hierarchy in Dense Associative Memory

Robin Thériault, Daniele Tantari

Dense Associative Memory (DAM) models have been attracting renewed attention since they were shown to be robust to adversarial examples and closely related to cutting edge machine…

cs.CR2026

Network Security under Heterogeneous Cyber-Risk Profiles and Contagion

Elisa Botteghi, Martino S. Centonze, Davide Pastorello +1

Cyber risk has become a critical financial threat in today's interconnected digital economy. This paper introduces a cyber-risk management framework for networked digital systems t…

cs.LG2025

Modeling Structured Data Learning with Restricted Boltzmann Machines in the Teacher-Student Setting

Robin Thériault, Francesco Tosello, Daniele Tantari

Restricted Boltzmann machines (RBM) are generative models capable to learn data with a rich underlying structure. We study the teacher-student setting where a student RBM learns st…