BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Algorithms for mean-field variational inference via polyhedral opt
 imization in the Wasserstein space
DTSTART:20240306T131500
DTEND:20240306T141500
DTSTAMP:20260406T212906Z
UID:2d39b333731fe0c4cbf8b7d8699343234625e2019ca7a34dda2da9c6
CATEGORIES:Conferences - Seminars
DESCRIPTION:Aram-Alexandre Pooladian (NYU)\nWe develop a theory of finite-
 dimensional polyhedral subsets over the Wasserstein space and optimization
  of functionals over them via first-order methods. Our main application is
  to the problem of mean-field variational inference\, which seeks to appro
 ximate a distribution\, called the posterior\, by the closest product meas
 ure in the sense of Kullback--Leibler divergence\, called the mean-field a
 pproximation. We propose a novel optimization procedure for computing the 
 mean-field approximation\, where we are able to provide concrete algorithm
 ic guarantees under the standard assumption that the posterior is strongly
  log-concave and log-smooth. Joint work with Yiheng Jiang and Sinho Chewi.
LOCATION:GA 3 21 https://plan.epfl.ch/?room==GA%203%2021
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR