BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Uday V. Shanbhag (Pennsylvania State University)
DTSTART:20201102T143000Z
DTEND:20201102T153000Z
DTSTAMP:20260423T021008Z
UID:OWOS/28
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/OWOS/28/">In
 exact and Distributed Best-Response Schemes for Stochastic Nash Equilibriu
 m Problems</a>\nby Uday V. Shanbhag (Pennsylvania State University) as par
 t of One World Optimization seminar\n\n\nAbstract\nWe consider the class o
 f Nash equilibrium problems where players solve convex optimization proble
 ms with expectation-valued objectives. In the first part of the presentati
 on\, we discuss a class of inexact best-response schemes in which an inexa
 ct best-response step is computed via stochastic approximation. We conside
 r synchronous\, asynchronous\, and randomized schemes and provide rate and
  complexity guarantees in each instance. In the second part of the present
 ation\, we consider distributed best-response schemes for aggregative game
 s. In such settings\, an (inexact) best-response step is overlaid with a c
 onsensus step. In addition to the oracle and iteration complexity\, we exa
 mine the communication complexity of such schemes for computing suitably d
 efined ϵ-stochastic Nash equilibria.\n\nThis first part of this is joint 
 work with Jinlong Lei\, Jong-Shi Pang and Suvrajeet Sen while the second p
 art of this work is joint with Jinlong Lei.\n\nThe address and password of
  the zoom room of the seminar are sent by e-mail on the mailinglist of the
  seminar one day before each talk\n
LOCATION:https://researchseminars.org/talk/OWOS/28/
END:VEVENT
END:VCALENDAR