Description

Mathematical research around the world is currently focused on integrating sound mathematical principles into artificial intelligence tools. This effort is aimed at developing innovative methods for machine learning (ML) and deep neural networks (DNNs) that can tackle key emerging challenges, including nonlinearity, non-smoothness, and non-convexity in high-dimensional probability and optimization, while also improving resource utilization and meeting sustainability goals.

The purpose of this event on Advanced Numerical Methods for Machine and Deep Learning is to offer a research-oriented introduction to stochastic numerical optimization algorithms, randomization in numerical linear algebra, regularization techniques, uncertainty quantification, and their applications in engineering and inverse imaging problems.

The event is designed for PhD students, as well as early career researchers (e.g. post-docs) with a background in applied mathematics, computer science, engineering or physics.    

The event consists of four theoretical blocks, each taught by a different lecturer. Each of the 4 blocks (5 hours each) is complemented by a lab session (2 hours) and/or exercise session (2 hours).

Confirmed lecturers

• Giovanni S. Alberti, MaLGa & University of Genoa

• Elena Celledoni, Norwegian University of Science and Technology (NTNU)

• Nataša Krklec Jerinkić, University of Novi Sad 

• Joel A. Tropp, Caltech 

Computational Lab

• Federica Porta, University of Modena and Reggio Emilia

• Luca Ratti, University of Bologna

Invited speakers

• Stefania Bellavia, University of Florence

• Sandra Pieraccini, Polytechnic University of Turin

• Silvia Villa, MaLGa & University of Genoa