Andrea Montanari on Machine Learning

Continuing to provide ways for scientists to interact online amid a global pandemic, ICTP is pleased to co-host a Colloquium given by Andrea Montanari of Stanford University, USA. Entitled "What is Machine Learning and What We Don't Understand About It," the online talk will be held on Wednesday, 22 July, 2020, at 16:00 CET. 

To join, please pre-register. Joining information will then be sent to you. The Colloqium will also be live-streamed and later posted on ICTP’s Youtube channel. The talk will be followed by a question and answer session. 

ICTP is joining the Scuola Internazionale Superiore di Studi Avanzati (SISSA) to host this event. The two Trieste-based institutions share many common research communities, including many scientists interested in different applications of machine learning. Montanari has been a Full Professor in the Departments of Electrical Engineering and Statistics at Stanford University since 2015, and is interested in the mathematical underpinnings of machine learning, 

Abstract: 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. I will try to provide a gentle introduction to the subject, and a peek into some recent advances towards addressing these challenges.