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:67@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20251208T160000
DTEND;TZID=Europe/Paris:20251208T160000
DTSTAMP:20260602T130205Z
URL:https://isdm.umontpellier.fr/events/secure-noise-sampling-for-differen
 tially-private-collaborative-learning-2/
SUMMARY:Secure Noise Sampling for Differentially Private Collaborative Lear
 ning
DESCRIPTION:Inria Montpellier\, St-Priest Campus\, Building 5\, Room 02/124
 \nMachine Learning in Montpellier\, Theory et Practice - Emmy Fang &amp\; 
 Arielle Zhang\n \nMachine Learning (ML) models typically benefit from acce
 ss to large and diverse datasets across different parties. However\, priva
 cy concerns often prohibit direct data sharing or centralized data aggrega
 tion. To address this\, various collaborative training frameworks have bee
 n proposed that enable joint model training while adhering to differential
  privacy (DP)\, the current golden standard privacy definition. In this ta
 lk\, I will provide an overview of existing privacy-preserving collaborati
 ve ML frameworks\, highlighting their core techniques and their limitation
 s. [...]\n \nIA et Experts
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2025/07/ml-mtp.png
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR