## Carlo Lucibello

I am an Assistant Professor of Computer Science at Bocconi University. I earned my PhD in Physics in 2015 from Sapienza University, under the supervision of Giorgio Parisi and Federico Ricci-Tersenghi. My research leverages analytical methods from statistical physics to deepen the theoretical understanding of machine learning and neural networks. I develop efficient, physics-inspired algorithms for learning, optimization, and inference.

Research interests

Neural Networks, Machine Learning, Statistical Inference, Disordered Systems, Statistical Physics, Combinatorial Optimization.

Selected Publications

## One-dimensional disordered Ising models by replica and cavity methods

PHYSICAL REVIEW. E, STATISTICAL, NONLINEAR AND SOFT MATTER PHYSICS, 2014## The statistical mechanics of random set packing and a generalization of the Karp-Sipser algorithm

INTERNATIONAL JOURNAL OF STATISTICAL MECHANICS, 2014## Loop expansion around the Bethe solution for the random magnetic field Ising ferromagnets at zero temperature

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2020## Critical initialisation in continuous approximations of binary neural networks

International Conference on Learning Representations, 2020## Finite-size corrections to disordered Ising models on random regular graphs

PHYSICAL REVIEW. E, STATISTICAL, NONLINEAR AND SOFT MATTER PHYSICS, 2014## Finite-size corrections to disordered systems on Erdös-Rényi random graphs

PHYSICAL REVIEW. B, CONDENSED MATTER AND MATERIALS PHYSICS, 2013## Anomalous finite size corrections in random field models

JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT, 2014## Scaling hypothesis for the Euclidean bipartite matching problem

PHYSICAL REVIEW E, STATISTICAL, NONLINEAR, AND SOFT MATTER PHYSICS, 2014## Loop expansion around the Bethe approximation through the M-layer construction

JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT, 2017## Generalized approximate survey propagation for high-dimensional estimation

Proceedings of Machine Learning Research. Vol. 97: International Conference on Machine Learning, 9-15 June 2019, Long Beach, California, USA, 2019## Reconstruction of pairwise interactions using Energy-Based Models

Proceedings of Machine Learning Research vol 145: 2nd Annual Conference on Mathematical and Scientific Machine Learning, Forthcoming## Deep learning via message passing algorithms based on belief propagation

MACHINE LEARNING: SCIENCE AND TECHNOLOGY, 2022## Neural networks: from the perceptron to deep nets

Spin glass theory and far beyond : replica symmetry breaking after 40 years, 2023## Interpretable pairwise distillations for generative protein sequence models

PLOS COMPUTATIONAL BIOLOGY, 2022Teaching

I’m currently teaching Python programming courses at the Bachelor and MSc level, and Machine Learning courses at the Bachelor and PhD level.