Mathematical problems in modern machine learning – Andrea Montanari (Stanford University)


The last fifteen years have witnessed dramatic advances in machine learning. This progress was mainly driven by engineering advances: greater computing power, and larger availability of training data. Not only the collection of methods that emerged from this revolution are not well understood mathematically, but they actually appear to defy traditional mathematical theories of machine learning. I will argue that future developments and applications will require to understand better the underlying mathematical principles. I will describe two recent examples of mathematical progress in this area that are connected to areas of modern mathematics: Gradient flows in Wasserstein spaces; Random matrix theory. [Based on joint work with: Song Mei, Phan-Minh Nguyen, Behrooz Ghorbani, Theodor Misiakiewicz]

In order to attend the online seminar, you can connect to: (needs authorization if you do not have a UniPi account and it is limited to 250 participants). The seminar will be also streamed live on the YouTube channel of the Department at the URL

Torna in cima