5 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 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…
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…
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…
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…