Mike Rabbat

Research Scientist

I am a Research Scientist in the Facebook AI Research group. I am currently on leave from McGill University where I am an Associate Professor of Electrical and Computer Engineering. I received a Masters from Rice University in 2003 and a PhD from the University of Wisconsin in 2006, both under the supervision of Robert Nowak.


Optimization, machine learning, parallel algorithms, graphs and networks, signal processing.

Latest Publications

CDC - December 14, 2020

Stability of Decentralized Gradient Descent in Open Multi-Agent Systems

Julien M. Hendrickx, Mike Rabbat

ICASSP - May 4, 2020

Lookahead converges to stationary points of smooth non-convex functions

Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Mike Rabbat

ICLR - April 26, 2020

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Mike Rabbat

NeurIPS - December 9, 2019

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

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

Workshop on ML for Systems at NeurIPS - November 30, 2019

MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions

Viswanath Sivakumar, Tim Rocktäschel, Alexander H. Miller, Heinrich Küttler, Nantas Nardelli, Mike Rabbat, Joelle Pineau, Sebastian Riedel

ICML - June 10, 2019

Stochastic Gradient Push for Distributed Deep Learning

Mahmoud Assran, Nicolas Loizou, Nicolas Ballas, Mike Rabbat

IEEE ICASSP - May 12, 2019

Provably Accelerated Randomized Gossip Algorithms

Nicolas Loizou, Mike Rabbat, Peter Richtárik

IEEE Signal Processing Magazine - May 1, 2019

Learning graphs from data: A signal representation perspective

Xiaowen Dong, Dorina Thanou, Mike Rabbat, Pascal Frossard

Proceedings of the IEEE - May 15, 2018

Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization

Angelica Nedic, Alex Olshevsky, Mike Rabbat