Mike Rabbat

Research Scientist

Facebook AI Research

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.

Interests

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

Google Scholar Profile
Google Scholar Profile

Latest Publications

Lookahead converges to stationary points of smooth non-convex functions

Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Mike Rabbat

ICASSP - May 4, 2020

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Mike Rabbat

ICLR - April 26, 2020

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

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

NeurIPS - December 9, 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

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

Stochastic Gradient Push for Distributed Deep Learning

Mahmoud Assran, Nicolas Loizou, Nicolas Ballas, Mike Rabbat

ICML - June 10, 2019

Provably Accelerated Randomized Gossip Algorithms

Nicolas Loizou, Mike Rabbat, Peter Richtárik

IEEE ICASSP - May 12, 2019

Learning graphs from data: A signal representation perspective

Xiaowen Dong, Dorina Thanou, Mike Rabbat, Pascal Frossard

IEEE Signal Processing Magazine - May 1, 2019

Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization

Angelica Nedic, Alex Olshevsky, Mike Rabbat

Proceedings of the IEEE - May 15, 2018