BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Multi-Agent Learning under Uncertainty: Equilibria\, Robustness & 
 Stability
DTSTART:20260316T111500
DTEND:20260316T120000
DTSTAMP:20260407T101420Z
UID:754d723b63affc1395f501d80ced74d9383b7f79ea85670c4b86182e
CATEGORIES:Conferences - Seminars
DESCRIPTION:Kyriakos Lotidis Ph.D. candidate in Operations Research\n\nSta
 nford University\, USA.\nAbstract:\nModern AI systems\, from autonomous ve
 hicles to digital marketplaces\, operate in decentralized environments cha
 racterized by strategic interaction\, noisy feedback\, and imperfect infor
 mation. Motivated by these challenges\, we study the interplay between rob
 ustness\, learning\, and uncertainty in continuous games. We first investi
 gate which equilibria persist under perturbations and introduce a structur
 al notion of equilibrium robustness based on the geometry of the underlyin
 g game. We then analyze the long-run behavior of adaptive agents learning 
 in such environments\, identifying conditions under which robust equilibri
 a emerge as stable outcomes of the learning dynamics. When classical conve
 rgence fails\, we further examine the stochastic behavior of these dynamic
 s\, studying when they admit a stationary distribution and how it concentr
 ates around equilibrium. Together\, these results contribute to our unders
 tanding of how equilibrium stability and learning dynamics interact under 
 uncertainty\, highlighting both the strengths and limitations of regulariz
 ation-based learning in multi-agent systems.\n\nBiography:\nKyriakos Lotid
 is is a final-year Ph.D. candidate in Operations Research at Stanford Univ
 ersity. His research lies at the intersection of game theory\, online lear
 ning\, and stochastic methods\, with a particular focus on the stability a
 nd convergence of learning algorithms in multi-agent systems. He also hold
 s an M.Sc. in Statistics from Stanford University and a B.Sc. in Electrica
 l and Computer Engineering from the National Technical University of Athen
 s.\n 
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR