BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Streaming Computation of Optimal Weak Transport Barycenters
DTSTART:20201211T151500
DTEND:20201211T163000
DTSTAMP:20260406T014646Z
UID:093d7675866e9b316a1253e70aa794960c8b757418c4edb37f0cbe86
CATEGORIES:Conferences - Seminars
DESCRIPTION:Elsa Cazelles\, CNRS\, IRIT\, Université de Toulouse\nWe prop
 ose an alternative to the standard Wasserstein barycenter problem for prob
 ability distributions\, based on optimal weak mass transport\, related to 
 martingale optimal transport. The main advantage of our proposal\, termed 
 weak barycenter\, is that it provides a framework for aggregating a set of
  probability measures\, analogous to the Wasserstein barycenter\, yet allo
 wing the construction of a stochastic iterative algorithm suited for a mor
 e general class of probability measures.\n\nThe proposed weak barycenter i
 s indeed solution of a fixed-point equation\, which also caters for the ca
 se of streams of distributions. We therefore provide a theoretical analysi
 s of the weak barycenter problem and of our algorithm\, in two settings: (
 i) for a finite number of measures and (ii) for a population of probabilit
 y measures distributed according to a given law on the Wasserstein space. 
 The proposed weak barycenter approach is illustrated on synthetic examples
  and validated on experiments using 1D and 2D real-world data.\n 
LOCATION:zoom https://epfl.zoom.us/j/85056864610
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR