The last fifteen years have witnessed dramatic breakthroughs in machine learning. This progress was crucially 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. Future developments and applications, especially within the sciences, will require to understand better the underlying mathematical principles. Professor Montanari will try to provide a gentle introduction to the subject, and a peek into some recent advances towards addressing these challenges.
Andrea Montanari is Full Professor in the Departments of Electrical Engineering and Statistics at Stanford University.
The seminar will take place online via Zoom platform. Register here
The video recording will be made available later on. Live screening in the Budinich Lecture Hall (ICTP) will be set up as well. Due to the safety measures that are in place, a maximum of 10 can attend by keeping distances and wearing a mask.