BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Learning Equilibria in Strategic Asymmetric Environments
DTSTART:20260211T111500
DTEND:20260211T120000
DTSTAMP:20260601T134201Z
UID:2711412cac6dda5991d3b3f654bf285256bc48dc4668904eaefdb3ba
CATEGORIES:Conferences - Seminars
DESCRIPTION:Francesco Bacchiocchi\, ELLIS PhD student in ELLIS PhD studen
 t in Computer Science at Politecnico di Milano\,Italy\nAbstract:\nEvery da
 y\, a very large number of users interact with digital platforms such as o
 nline advertising platforms or crowdsourcing marketplaces. These interacti
 ons are characterized by a strong asymmetry\, not only in objectives\, but
  also in the information available to users and to the centralized platfor
 m. Game theory has traditionally captured the nature of such interactions 
 through the notion of Stackelberg equilibrium\, where the platform acts as
  a leader by committing to a certain strategy and users\, acting as follow
 ers\, respond based on their private information and objectives. However\,
  most existing work mainly focuses on static environments in which the lea
 der knows everything about the followers beforehand. In practice\, this as
 sumption rarely holds. Platforms must set prices\, incentives\, or informa
 tion policies under substantial uncertainty. In this talk\, we show how th
 is limitation can be overcome by studying how Stackelberg equilibria can b
 e learned through repeated interactions in different settings at the core 
 of today’s digital economies\, using data-driven\, no-regret\, and sampl
 e-efficient techniques\, even when users’ preferences are initially unkn
 own.\n\nBiography:\nFrancesco Bacchiocchi is an ELLIS PhD student in Compu
 ter Science at Politecnico di Milano\, supervised by Prof. Nicola Gatti an
 d Prof. Jiarui Gan at the University of Oxford. He received both the M.Sc.
  and the B.Sc. in Mathematical Engineering from Politecnico di Milano. His
  research lies at the intersection of algorithmic game theory and online l
 earning\, with the goal of understanding how strategic agents behave in dy
 namic environments. His work has been published at top ML venues\, receivi
 ng oral and spotlight presentations.\n 
LOCATION:ME C2 405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR