Seminar
| Parent Program: | |
|---|---|
| Location: | SLMath: Eisenbud Auditorium, Online/Virtual |
Keywords and Mathematics Subject Classification (MSC)
Primary Mathematics Subject Classification
No Primary AMS MSC
Secondary Mathematics Subject Classification
No Secondary AMS MSC
Graduate Students Seminar Geometry of No-Regret Learning in Games
This seminar will delve into the long-run behavior of no-regret learning dynamics in a game-theoretic context from a geometrical standpoint. I will present a recent application of a decomposition technique to finite auctions, offering potential insights into the convergence patterns documented in the existing literature. Furthermore, I will present a new geometric characterization of population games for which no-regret learning exhibits cyclic and non-convergent behavior.
No Notes/Supplements Uploaded