A sketchy tour or large scale machine learning
Data: 2 Dicembre 2021
Luogo: Aula 5016 (Lab LM). A link for remote attendance will be provided in a reminder message a few days before the talk.
Speaker: Lorenzo Rosasco (Università degli Studi di Genova)
In this talk, I will review our recent efforts to derive provably efficient large scale machine learning solutions. The basic idea is that AI/ML systems are often redundant and can be compressed to increase efficiency with little/no loss of predictive accuracy. Based on this idea, I will focus on kernel based nonparametric approaches and describe results along three directions. The first is the derivation of theoretical guarantees in terms of both efficiency and optimal statistical accuracy. The second regards efficient implementations and corresponding software libraries. The third highlights some examples of applications in vision and high energy physics.
Lorenzo Rosasco is professor at University of Genova. He is also visiting professor at the Massachusetts Institute of Technology (MIT) and external collaborator at the Italian Technological Institute (IIT). He coordinates the Machine Learning Genova center (MaLGa) and the Laboratory for Computational and Statistical Learning focused on theory, algorithms and applications of machine learning. He received his PhD in 2006 from the University of Genova, after being a visiting student at the Center for Biological and Computational Learning at MIT, the Toyota Technological Institute at Chicago (TTI-Chicago) and the Johann Radon Institute for Computational and Applied Mathematics. Between 2006 and 2013 he was a postdoc and research scientist at the Brain and Cognitive Sciences Department at MIT. He is a fellow in Ellis, where he is co-director of the "Theory, Algorithms and Computations of Modern Learning Systems" program and the Ellis Genoa unit. He is a recipient of a number of grants, including a FIRB and an ERC consolidator.
Persona di riferimento: Nicolò Cesa-Bianchi
18 novembre 2021