CARLO LUCIBELLO

Courses a.y. 2023/2024
30554 MATHEMATICAL MODELLING IN MACHINE LEARNING
41001 MODERN APPLIED MACHINE LEARNING
Courses previous a.y.
I’m currently teaching Python programming courses at the Bachelor and MSc level, and Machine Learning courses at the Bachelor and PhD level.
Biographical note
I am Assistant Professor in Computer Science at Bocconi University. I obtained my PhD in Physics in 2015 from Sapienza University, under the supervision of Giorgio Parisi and Federico Ricci-Tersenghi. I’m mostly focused on applying analytical tools from statistical physics to the understeanding of machine learning problems and in deriving efficient physics-inspired algorithms for learning, optimization, and inference.
Research interests
Neural Networks, Statistical Inference, Disordered Systems, 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
One-loop diagrams in the random Euclidean matching problem
PHYSICAL REVIEW. E, 2017
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