Michael Rabbat

Mike is a founding member of the Facebook AI Research (FAIR) team in Montreal. He holds a B.Eng. from the University of Illinois at Urbana-Champaign, a M.Eng from Rice University, and a Ph.D. in electrical engineering from the University of Wisconsin-Madison. Prior to Facebook, Mike was a professor at McGill University in the Department of Electrical and Computer Engineering. His research interests include optimization, distributed algorithms and signal processing.

Michael's Publications

July 24, 2021

CORE MACHINE LEARNING

SYSTEMS RESEARCH

Federated Learning with Buffered Asynchronous Aggregation

Federated Learning (FL) trains a shared model across distributed devices while keeping the training data on the devices. Most FL schemes are synchronous: they perform a synchronized aggregation of model updates from individual devices. …

John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek, Dzmitry Huba

July 24, 2021

May 12, 2019

RESEARCH

ML APPLICATIONS

Provably Accelerated Randomized Gossip Algorithms

In this work we present novel provably accelerated gossip algorithms for solving the average consensus problem. The proposed protocols are inspired from the recently developed accelerated variants of the randomized Kaczmarz method – a popular…

Nicolas Loizou, Michael Rabbat, Peter Richtárik,

May 12, 2019

May 01, 2019

RESEARCH

SPEECH & AUDIO

Learning graphs from data: A signal representation perspective

The construction of a meaningful graph topology plays a crucial role in the effective representation, processing, analysis and visualization of structured data. When a natural choice of the graph is not readily available from the datasets, it…

Xiaowen Dong, Dorina Thanou, Michael Rabbat, Pascal Frossard,

May 01, 2019

December 09, 2019

RESEARCH

ML APPLICATIONS

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossip-based Actor-Learner Architectures (GALA) where several…

Mahmoud Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau, Michael Rabbat,

December 09, 2019