BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:8708@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20250704T160000
DTEND;TZID=Europe/Paris:20250704T170000
DTSTAMP:20250626T081533Z
URL:https://www.i2m.univ-amu.fr/evenements/differentiable-mixture-wasserst
 ein/
SUMMARY:Julie Delon (Université Paris Cité (MAP5)): Differentiable Mixtur
 e Wasserstein
DESCRIPTION:Julie Delon: Gaussian Mixture Models (GMMs) are widely used in 
 applied fields to represent the probability distributions of real-world da
 tasets. While optimal transport can compute distances or geodesics between
  such mixture models\, the corresponding Wasserstein geodesics do not pres
 erve the property of being a GMM. A few years ago\, it was demonstrated th
 at restricting the set of possible coupling measures to GMMs transforms th
 e original infinitely dimensional optimal transport problem into a finite-
 dimensional problem with a simple discrete formulation. The resulting Mixt
 ure Wasserstein distance is particularly well-suited for applications wher
 e a clustering structure is present in the data.\n\nTo make this framework
  compatible with discrete data\, such as those used in machine learning ap
 plications\, one approach is to use an inference algorithm like Expectatio
 n-Maximization to infer the parameters of the GMMs from the data. In this 
 talk\, after a brief overview of Mixture Wasserstein\, we will explore how
  to make the entire framework differentiable. This enables the use of this
  distance for various machine learning and image processing tasks where th
 e differentiability is key.
CATEGORIES:Colloquium
LOCATION:Saint-Charles - FRUMAM  (2ème étage)\, 3 Place Victor Hugo\, Mar
 seille\, 13003\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=3 Place Victor Hugo\, Marse
 ille\, 13003\, France;X-APPLE-RADIUS=100;X-TITLE=Saint-Charles - FRUMAM  (
 2ème étage):geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR