Online Learning and Economics

Please note this is a two-day event and participants need to be able to join on both days.

Online learning investigates problems where data is revealed sequentially and used to forecast the best action to undertake at each step. Its online essence naturally captures economic problems, like pricing or repeated auctions, where agents have to learn ''on the fly'' the relevant features of the environment (e.g., competition, demand, or supply) and are penalized for each suboptimal choice (e.g., if they underbid and lose a valuable item). Furthermore, online learning provides a natural framework to study dynamics that converge to game-theoretic equilibria.
The course aims to provide an introduction to online learning and present the current research directions; the students will learn the technical toolbox of online learning as well as the main results in the area, with a specific focus on economic applications.

An agenda for each day of this event will be shared in advance of the day.

Presenter Bio: Federico Fusco is an Assistant Professor at the Department of Computer, Control and Management Engineering at Sapienza University of Rome. Previously, he was a PostDoc and completed his PhD under the supervision of Stefano Leonardi at the same University. During his Ph.D., he was hosted by Paul Duetting at Google Research Zurich as a research intern and then as a student researcher. Federico's research interests span Algorithmic Game Theory, Online Learning, and Submodular Maximization.

Host or Publisher King’s Institute for Artificial Intelligence