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:389@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20240910T140000
DTEND;TZID=Europe/Paris:20240910T140000
DTSTAMP:20260828T114259Z
URL:https://isdm.umontpellier.fr/events/over-parameterisation-and-overfitt
 ing-myths-theories-and-tools-2/
SUMMARY:Over-parameterisation and Overfitting: Myths\, Theories and Tools
DESCRIPTION:Room 02.124\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice\n\nOverfitting on training data i
 s typically assumed to be a bad practice. However\, modern machine learnin
 g models are highly over-parameterised\, to the extent that they can overf
 it on training data. In this talk\, I will discuss new theories that debun
 k the myths that: (1) large models with too many parameters always overfit
  the training data\; and (2) models that perfectly fit the training data c
 annot predict well on new data.I will then present our recent works on gen
 eralisation and learning dynamics of over-parameterised models\, including
  (1) the double descent phenomenon in causal inference and (2) the neural 
 tangent kernel approximation for semi- and self-supervised models. I will 
 highlight how some of our results resolve conjectures in machine learning\
 , and also provide new practical tools.\,\,\n\nMachine Learning in Montpel
 lier\, Theory &amp\; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Saint Priest Campus - Building 5 - Room 02.124\, 860 rue St Priest
 \, Montpellier\, 
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=860 rue St Priest\, Montpel
 lier\, ;X-APPLE-RADIUS=100;X-TITLE=Saint Priest Campus - Building 5 - Room
  02.124:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR