“Big Thought Time Talk” by Nokia: “Fast Distributed Optimization with Asynchrony and Time Delays”

Speaker : Laurent Massoulié
Inria
Date: 21/10/2021
Time: 5:00 pm - 6:00 pm
Location: LINCS + Teams

Abstract

The training of models over distributed data calls for distributed optimization schemes. This has motivated research on distributed convex optimization, leading to the identification of lower bounds on convergence speed, and distributed optimization algorithms with convergence speed potentially matching these lower bounds, for a variety of settings.

In this talk we focus on the important setting of asynchronous operation, for which we propose optimization algorithms with optimal speed. We next consider systems with heterogeneous communication and computation delays, for which we propose fast asynchronous algorithms adapted to these heterogeneous delays.

Bio:
Laurent Massoulié is research director at Inria, head of the Microsoft Research – Inria Joint Centre, and professor at the Applied Maths Centre of Ecole Polytechnique. His research interests are in machine learning, probabilistic modelling and algorithms for networks. He has held research scientist positions at: France Telecom, Microsoft Research, Thomson-Technicolor, where he headed the Paris Research Lab. He obtained best paper awards at IEEE INFOCOM 1999, ACM SIGMETRICS 2005, ACM CoNEXT 2007, NeurIPS 2018, was elected “Technicolor Fellow” in 2011, received the  “Grand Prix Scientifique” of the Del Duca Foundation delivered by the French Academy of Science in 2017, and is a Fellow of the LINCS Laboratory.

LINCS hosted this talk in its premises at 23 avenue d’Italie. 
 
**The talk was organised by Nokia in the framework of its “Big Thought Time Talk” series. All institutional parteners of the LINCS, including Nokia and Inria, have indeed long-standing partnership in solving future network challenges as well as the role of machines in automating and augmenting human existence.