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:250@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20241114T140000
DTEND;TZID=Europe/Paris:20241114T140000
DTSTAMP:20260825T134859Z
URL:https://isdm.umontpellier.fr/events/taming-heterogeneity-in-federated-
 linear-stochastic-approximation-and-federated-learning/
SUMMARY:Taming Heterogeneity in Federated Linear Stochastic Approximation a
 nd Federated Learning
DESCRIPTION:Room 02.022\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice\n\nIn federated learning\, multip
 le agents collaboratively train a machine learning model without exchangin
 g local data. To achieve this\, each agent locally updates a global model\
 , and the updated models are periodically aggregated by a central server. 
 In this talk\, I will first focus on federated linear stochastic approxima
 tion (FedLSA)\, with an emphasis on agent heterogeneity. I will derive upp
 er bounds on the sample and communication complexity of FedLSA and present
  a method to reduce communication costs using control variates. Special at
 tention will be given to the "linear speed-up" phenomenon\, demonstrating 
 that the sample complexity scales inversely with the number of agents in b
 oth methods. Finally\, I will discuss possible extensions of these results
  to non-linear federated learning and provide first-order expansions of th
 e bias in federated averaging.\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 02.022\, 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