BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Algorithms for Distributed and Collaborative Deep Learning
DTSTART:20231116T133000
DTEND:20231116T143000
DTSTAMP:20260406T020347Z
UID:3af00f0073f6a913f1bed0167c2da6413d4c22b06a4ea6c1a32b409e
CATEGORIES:Conferences - Seminars
DESCRIPTION:Anastasiia Koloskova\, graduating doctoral student in Machine 
 Learning and Optimization Laboratory\, EPFL\nEDIC Mock interview public ta
 lk announcement to prepare for hiring interviews within academia\n\nAbstra
 ct\nIn distributed learning\, multiple workers (e.g.\, GPUs) contribute in
  parallel to expedite the training of machine learning models. In collabor
 ative learning\, the training data is distributed among several participan
 ts due to the privacy-sensitive nature of the data. These participants col
 laborate together to solve a common machine learning task. In this talk\, 
 I will discuss various challenges encountered in both scenarios\, includin
 g communication efficiency\, data heterogeneity\, and privacy protection o
 f the training data.\n\nBio\nI am a PhD student at EPFL at the laboratory 
 of Optimization and Machine Learning with Prof. Martin Jaggi. My research 
 is focused on distributed optimization for machine learning and collaborat
 ive learning. During my studies I was awarded a Google PhD Fellowship in M
 achine Learning. \n\n 
LOCATION:BC 410 https://plan.epfl.ch/?room==BC%20410
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR