Image of Our Mission
Our Mission

The Artificial Intelligence Lab at Bocconi, part of the BIDSA institute, comprises a multidisciplinary group of researchers conducting theoretical, algorithmic and applied studies on intelligent systems, building on tools from computer science, statistical physics, economics, statistics and computational biology.

more

Focus on

Image of ELLIS Online workshop on QPhML on 6-8 July 2020
online
-
ELLIS Online workshop on QPhML on 6-8 July 2020
Image of "Rough-glassy landscapes from inference to machine learning”
Room 3-e4-sr03 - Via G. Rontgen, 1 (floor 3)
-
Total Search Problems and Cryptography, Alon Rosen (Herzliya Interdisciplinary Center)
Image of "Rough-glassy landscapes from inference to machine learning”
Room 3-e4-sr03 - Via G. Rontgen, 1 (floor 3)
-
Bayesian Auctions with Efficient Queries, Jing Chen (Stony Brook University)
Image of "Rough-glassy landscapes from inference to machine learning”
BOCCONI UNIVERSITY - PEREGO HALL
-
Seminar on Machine Learning and Business - Vodafone Chair in Machine Learning and Data Science

Research

Image of Algorithms

Algorithms

We study and develop various classes of inference and optimization algorithms, ranging from MCMC to message-passing and SGD methods.
Image of Cognitive Modeling

Cognitive Modeling

We study stochastic learning/discovery processes in physically constrained models (e.g. with limited precision, energy, deliberation time etc.) of interest in the neurosciences and in novel hardware technologies.
Image of Games and Decisions

Games and Decisions

We study games (interactive decision situations) from both a prescriptive and a descriptive perspective. Our aim is to improve rational decision making, and to represent natural decision making.
Image of Machine Learning Theory

ML Theory

We aim at understanding the foundational principles underlying Machine Learning, using techniques from statistical physics and applied probability.
Image of Statistical Learning

Statistical Learning

We aim at providing methodological, theoretical and computational advances in uncertainty quantification and statistical learning of complex data and processes with special emphasis on Bayesian (nonparametric) approaches.
Image of Stochastic Optimization

Stochastic Optimization

We want to apply tools and algorithms from statistical physics, decision theory and machine learning to problems of optimization under uncertainty, e.g. those in which the loss landscape is unknown before exploration.