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:6108@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20220325T143000
DTEND;TZID=Europe/Paris:20220325T153000
DTSTAMP:20241120T200914Z
URL:https://www.i2m.univ-amu.fr/evenements/privacy-preserving-federated-le
 arning/
SUMMARY:Aurélien BELLET (INRIA Lille): Privacy-Preserving Federated Learni
 ng
DESCRIPTION:Aurélien BELLET: Federated learning (FL) is a machine learning
  paradigm where several participants collaboratively train a model while k
 eeping their data decentralized. However\, the model parameters or gradien
 ts exchanged during the FL training process may leak information about the
  data. After a brief introduction to FL\, I will show how to use the notio
 n of Differential Privacy (DP) to design FL algorithms that provably ensur
 e privacy and confidentiality. In particular\, I will present two approach
 es (one for server-orchestrated FL and one for fully decentralized FL) tha
 t nearly match the privacy-utility trade-off of the centralized setting wi
 thout relying on a trusted curator or complex secure computation primitive
 s.\n&nbsp\;
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 022/01/Aurelien_Bellet.jpg
CATEGORIES:Séminaire,Signal et Apprentissage
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20211031T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR