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:390@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20250306T140000
DTEND;TZID=Europe/Paris:20250306T140000
DTSTAMP:20260828T114310Z
URL:https://isdm.umontpellier.fr/events/how-should-we-construct-prediction
 -sets-insights-from-conformal-prediction-3/
SUMMARY:How Should We Construct Prediction Sets? Insights from Conformal Pr
 ediction
DESCRIPTION:Room 02.022\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice\n\nIn the first part of the talk\
 , I will present some reflections on the purpose of prediction sets and th
 e role that statistics can play in forming useful prediction sets. In part
 icular\, I will discuss how prediction sets fit into a decision making pip
 eline and the different kinds of decisions one may make using a prediction
  set. In the second part of the talk\, I will describe a particular statis
 tically motivated set-generating procedure for the classification setting 
 called clustered conformal prediction\, which gives all classes an equal c
 hance of being correctly included in the prediction set (“class-conditio
 nal coverage”). This procedure can be useful in situations where it is i
 mportant to identify instances of all classes\, even the rare ones. We dem
 onstrate the performance of this method on ImageNet and other image classi
 fication datasets.\n\nMachine Learning in Montpellier\, Theory &amp\; Prac
 tice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Room 02.022\, 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 02.022\, Building 5:g
 eo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR