BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Measure-theoretic Approaches and Optimal Transportation in Statist
 ics
DTSTART:20221121T080000Z
DTEND:20221125T170000Z
DTSTAMP:20260416T053800Z
UID:indico-event-7547@indico.math.cnrs.fr
CONTACT:gesda2022@ihp.fr
DESCRIPTION:Measure-theoretic Approaches and Optimal Transportation in Sta
 tistics21-25 November 2022 - IHP\, ParisThe Wasserstein distance in Optima
 l transportation has proved to be useful for a wide range of learning task
 s such as generative models\, domain adaptation or supervised embeddings. 
 It is also an important metric for Topological Data Analysis and Geometric
  inference. More generally\, distances on the space of probability measure
 s\, such as the maximum mean discrepancy\, have shown to be powerful tools
  in statistical learning. ProgramAbstracts  Invited SpeakersQuentin Ber
 thet (Google Research)Blanche Buet (LMO\, Orsay)Elsa Cazelles (IRIT\, Toul
 ouse)Nicolas Courty (IRISA\, Rennes)Jérôme Dedecker (MAP5\, Paris)Agnès
  Desolneux (Centre Borelli\, Saclay)Jean Feydy (HeKA\, INRIA Paris)Arthur 
 Gretton (UCL\, London)Théo Lacombe (LIGM\, Champs sur Marne)Thibaut Le Go
 uic (IMM\, Marseille)Christophe Ley (Université du Luxembourg)Jean-Michel
  Loubes (IMT\, Toulouse)Olga Mula (CEREMADE\, Dauphine)Axel Munk (Götting
 en & Planck)Quentin Paris (HSE\, Moscow)Giovanni Peccati (Luxemburg)Gabrie
 l Peyré (DMA\, ÉNS)Johan Segers (UC Louvain)Bodhisattva Sen (Columbia\, 
 New York)Bharath Kumar Sriperumbudur (Pennsylvania State University)Franç
 ois-Xavier Vialard (LIGM\, Université Gustave Eiffel)\n\nhttps://indico.m
 ath.cnrs.fr/event/7547/
IMAGE;VALUE=URI:https://indico.math.cnrs.fr/event/7547/logo-1140437517.png
LOCATION:Amphithéâtre Hermite (Institut Henri Poincaré )
URL:https://indico.math.cnrs.fr/event/7547/
END:VEVENT
END:VCALENDAR