On Wednesday, May 17th, at 12h00 in Aula 2001 (change of usual time and place! Aula 2001 is on the top floor of the Math Department, close to the copy shop) at Roma Tor Vergata, RoMaDS (https://www.mat.uniroma2.it/~rds/about.php) will host Daniele Calandriello (Google Deep Mind, Paris) with the seminar
“Efficient exploration in stochastic environments"
Abstract:
Machine learning has seen an explosive growth recently, driven mostly by breakthroughs in classification and generative models. However ML applications in decision making settings are much more limited, where data collection is much higher and ML models must be sufficiently robust and accurate to deal with unforeseen consequences and avoid worst case scenarios. In this talk we will introduce some classical results for online decision making in stochastic linear spaces, with applications to active learning, bandit/bayesian optimization and deep learning. Starting from a rigorous analysis of the noise propagation we can formulate provably robust (i.e. no-regret) algorithms, and then create variants that can scale to modern ML data regimes without sacrificing safety. And if time suffice, we will highlight how these approaches inspired a new wave of exploration techniques to enable reinforcement learning agents to solve extremely long horizon tasks.
We encourage in-person partecipation. Should you be unable to come, there will be a Teams link on our webpage published before the start of the talk.
The seminar is part of the Excellence Project MatMod@TOV.