BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:204@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20250624T140000
DTEND;TZID=Europe/Paris:20250624T140000
DTSTAMP:20260825T132148Z
URL:https://isdm.umontpellier.fr/events/generative-diffusions-and-minimax-
 estimation/
SUMMARY:Generative diffusions and minimax estimation
DESCRIPTION:Room 02.124\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice - Eddie Aamari (CNRS)\n\nThe aim 
 of this talk is to introduce generative models based on diffusions. After 
 a brief reminder of the key concepts of stochastic calculus\, we&apos\;ll 
 detail how a time-reversed Ornstein-Uhlenbeck process can be used to trans
 port distributions when starting from a Gaussian source. As this reversed 
 process involves the so-called score function\, we will then address the q
 uestion of score learning via the minimization of an empirical contrast. F
 inally\, we&apos\;ll discuss the stability of such a method\, as well as m
 inimax estimation speeds if time permits. Notes are available [ https://is
 dm.umontpellier.fr/www.math.ens.psl.eu/~eaamari/files/Diffusion-based%20ge
 nerative%20modeling%20-%20For%20statisticians%20and%20probabilists.pdf | h
 ere ] .\n\nMachine Learning in Montpellier\, Theory &amp\; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Room 02.124 Building 5\, St Priest Campus\, Montpellier\, 34000\, 
 France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=St Priest Campus\, Montpell
 ier\, 34000\, France;X-APPLE-RADIUS=100;X-TITLE=Room 02.124 Building 5: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