Seminario pubblico di Federico Fusco (Procedura valutativa per n.1 posto di Ricercatore a tempo determinato tipologia A - SC 09/H1 SSD ING-INF/05) - 21/03/23 ore 12.00, Aula Magna
Dr. Federico Fusco
Martedì, 21 March, 2023 - 12:00
DIAG - Aula Magna
Titolo: The bilateral trade problem from an online learning perspective: partial feedback and needles in the haystack
Bilateral trade, a fundamental topic in economics, models the problem of intermediating between two strategic agents, a seller and a buyer, willing to trade a good for which they hold private valuations. We cast the bilateral trade problem in a regret minimization framework over T rounds of seller/buyer interactions, with no prior knowledge on their private valuations.
Our main contribution is a nearly complete characterization of the regret regimes for fixed-price mechanisms with different feedback models and private valuations, using as a benchmark the best fixed-price in hindsight.
The talk is based on the following papers:
- Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi "Repeated Bilateral Trade Against a Smoothed Adversary", preprint on the arXiv, 2023
- Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi "Bilateral Trade: A Regret Minimization Perspective", Mathematics of Operations Research, 2023
- Yossi Azar, Amos Fiat, FF: "An α-regret Analysis of Adversarial Bilateral Trade". NeurIPS'22
- Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, FF, Stefano Leonardi: "A Regret Analysis of Bilateral Trade". EC, 2021
Federico Fusco is currently a Postdoc at Sapienza University of Rome, hosted by Stefano Leonardi.
Previously he completed his PhD in Data Science in the same University. He holds a Master Degree
in Mathematics from Sapienza University of Rome and from the Sapienza School of Advanced Studies.
During his PhD, Federico visited Milan University, hosted by Nicolò Cesa-Bianchi and Tel-Aviv University,
hosted by Michal Feldman. He has been a Research Intern and then a Research Student at Google Zurich,
hosted by Paul Duetting. His Research interests are Algorithmic Game Theory, Online Learning and Submodular
Maximization. He has published several papers in leading conferences in the area of Machine Learning, Algorithmic Theory,
Economics and Computation (Neurips, ICML, STOC, SODA, EC) and Journals (Math of OR, JAIR, JAAMAS).
gruppo di ricerca: