Contacts

Carlo Baldassi

CB-picture

Department of Computing Sciences

Associate Professor

carlo.baldassi@unibocconi.it

Bio

I graduated in Trieste in Theoretical Physics with a thesis in applications to Computer Science and large scale discrete optimization problems. I then moved to Turin where I did a PhD in Computational Neuroscience, and also got interested in Bioinformatics and inference problems. Throughout I kept an eye on theoretical aspects of Machine Learning and Neural Networks, which are my main focus lately.

About

I've been the director of the BSc in Mathematical and Computing Sciences for Artificial Intelligence (BAI) since 2023/24.

Research Interests

My research interests focus on the application of Statistical Mechanics to machine learning and computational neuroscience, and more generally to large-scale inference and optimization problems. Lately I've been particularly interested in studying the loss landscape of neural networks, analytically and numerically.

working papers

P Chaudhari, A Choromanska, S Soatto, Y LeCun, C Baldassi, C Borgs, J Chayes, L Sagun, R Zecchina

C Baldassi, F Gerace, HJ Kappen, C Lucibello, L Saglietti, E Tartaglione, R Zecchina

C Baldassi, R Zecchina

C Baldassi, EM Malatesta, R Zecchina

C Baldassi, F Pittorino, R Zecchina

Publications

Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses

PHYSICAL REVIEW LETTERS, 2015

Unreasonable effectiveness of learning neural networks: from accessible states and robust ensembles to basic algorithmic schemes

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016

Entropy-SGD: biasing gradient descent into wide valleys

JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT, 2019

Role of synaptic stochasticity in training low-precision neural networks

PHYSICAL REVIEW LETTERS, 2018

Efficiency of quantum vs. classical annealing in nonconvex learning problems

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2018

Properties of the geometry of solutions and capacity of multilayer neural networks with rectified linear unit activations

PHYSICAL REVIEW LETTERS, 2019

Shaping the learning landscape in neural networks around wide flat minima

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2020

Teaching

MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE

41046

COMPUTER SCIENCE I

MACHINE LEARNING II

30586

MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE LAB

Past years teaching

Additional teachings info

I teach and have taught a number of programming courses, from undergraduate to PhD level, using Python and Julia.