Mila > Team > Michael Rabbat

Michael Rabbat

Associate Industry Member
Adjunct Professor, McGill University, Facebook

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.

Publications

2021-11

Papaya: Practical, Private, and Scalable Federated Learning.
Dzmitry Huba, John Nguyen, Kshitiz Malik, Ruiyu Zhu, Mike Rabbat, Ashkan Yousefpour, Carole-Jean Wu, Hongyuan Zhan, Pavel Ustinov, Harish Srinivas, Kaikai Wang, Anthony Shoumikhin, Jesik Min and Mani Malek
arXiv preprint arXiv:2111.04877
(2021-11-08)
dblp.uni-trier.dePDF

2021-10

Sustainable AI: Environmental Implications, Challenges and Opportunities.
Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona Aga Behram, James Huang, Charles Bai, Michael Gschwind, Anurag Gupta, Myle Ott, Anastasia Melnikov, Salvatore Candido, David Brooks, Geeta Chauhan, Benjamin Lee, Hsien-Hsin S. Lee, Bugra Akyildiz... (5 more)
arXiv preprint arXiv:2111.00364
(2021-10-30)
dblp.uni-trier.dePDF
Trade-offs of Local SGD at Scale: An Empirical Study.
Jose Javier Gonzalez Ortiz, Jonathan Frankle, Mike Rabbat, Ari S. Morcos and Nicolas Ballas
arXiv preprint arXiv:2110.08133
(2021-10-15)
dblp.uni-trier.dePDF

2021-06

Stochastic Polyak Stepsize with a Moving Target
Robert M. Gower, Aaron Defazio and Michael G. Rabbat
arXiv preprint arXiv:2106.11851
(2021-06-22)
128.84.4.27PDF
Federated Learning with Buffered Asynchronous Aggregation.
John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek Esmaeili and Dzmitry Huba
arXiv preprint arXiv:2106.06639
(2021-06-11)
ui.adsabs.harvard.eduPDF

2021-05

A Closer Look at Codistillation for Distributed Training
Shagun Sodhani, Olivier Delalleau, Mido Assran, Koustuv Sinha, Nicolas Ballas and Michael Rabbat
arXiv e-prints
(2021-05-04)
ui.adsabs.harvard.eduPDF
Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
Mido Assran, Nicolas Ballas, Lluis Castrejon and Michael Rabbat
arXiv e-prints
(2021-05-04)
ui.adsabs.harvard.eduPDF

2021-03

Learning with Gradient Descent and Weakly Convex Losses
Dominic Richards and Mike Rabbat
Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery
Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark C. Jeffrey, Vikram Saraph, Bor-Yiing Su, Caroline Trippel, Jiyan Yang, Mike Rabbat, Brandon Lucia and Carole-Jean Wu
Proceedings of Machine Learning and Systems
(2021-03-15)
proceedings.mlsys.orgPDF

2021-01

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments With Support Samples
Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Armand Joulin, Nicolas Ballas and Michael G. Rabbat
Asynchronous Gradient Push
Mahmoud S. Assran and Michael G. Rabbat
IEEE Transactions on Automatic Control
(2021-01-01)
doi.org

2020-12

Stability of Decentralized Gradient Descent in Open Multi-Agent Systems
Julien M. Hendrickx and Michael G. Rabbat
Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
Florian Knoll, Tullie Murrell, Anuroop Sriram, Nafissa Yakubova, Jure Zbontar, Michael G. Rabbat, Aaron Defazio, Matthew J. Muckley, Daniel K. Sodickson, C. Lawrence Zitnick and Michael P. Recht

2020-11

CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery
Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark C. Jeffrey, Vikram Saraph, Bor-Yiing Su, Caroline Trippel, Jiyan Yang, Mike Rabbat, Brandon Lucia and Carole-Jean Wu
arXiv preprint arXiv:2011.02999
(2020-11-05)
ui.adsabs.harvard.eduPDF

2020-10

Optimization for Data-Driven Learning and Control
Usman A. Khan, Waheed U. Bajwa, Angelia Nedic, Michael G. Rabbat and Ali H. Sayed
Proceedings of the IEEE
(2020-10-27)
asu.pure.elsevier.com
Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study.
Michael P. Recht, Jure Zbontar, Daniel K. Sodickson, Florian Knoll, Nafissa Yakubova, Anuroop Sriram, Tullie Murrell, Aaron Defazio, Michael Rabbat, Leon Rybak, Mitchell Kline, Gina Ciavarra, Erin F. Alaia, Mohammad Samim, William R. Walter, Dana J. Lin, Yvonne W. Lui, Matthew Muckley, Zhengnan Huang, Patricia Johnson... (2 more)
American Journal of Roentgenology
(2020-10-14)
nyuscholars.nyu.edu
Advances in Asynchronous Parallel and Distributed Optimization
Mahmoud Assran, Arda Aytekin, Hamid Reza Feyzmahdavian, Mikael Johansson and Michael G. Rabbat

2020-07

On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
Mahmoud Assran and Michael Rabbat

2020-06

Recovering Petaflops in Contrastive Semi-Supervised Learning of Visual Representations.
Mahmoud Assran, Nicolas Ballas, Lluís Castrejón and Michael G. Rabbat
arXiv preprint arXiv:2006.10803
(2020-06-18)
dblp.uni-trier.de

2020-05

Lookahead Converges to Stationary Points of Smooth Non-convex Functions
Jianyu Wang, Vinayak Tantia, Nicolas Ballas and Michael Rabbat
ICASSP 2020
(2020-05-04)
doi.org

2020-04

SloMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
Jianyu Wang, Vinayak Tantia, Nicolas Ballas and Michael Rabbat
ICLR 2020
(2020-04-30)
iclr.ccPDF

2020-03

Asynchronous Gradient-Push
Mahmoud Assran and Michael Rabbat
IEEE Transactions on Automatic Control
(2020-03-02)
xplorestaging.ieee.org

2020-01

fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning.
Florian Knoll, Jure Zbontar, Anuroop Sriram, Matthew J Muckley, Mary Bruno, Aaron Defazio, Marc Parente, Krzysztof J Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzalv, Adriana Romero, Michael Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C Lawrence Zitnick... (3 more)
Radiology. Artificial intelligence
(2020-01-29)
europepmc.orgPDF

2019-10

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 and Sebastian Riedel
arXiv preprint arXiv:1910.04054
(2019-10-09)
ui.adsabs.harvard.eduPDF
SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
Jianyu Wang, Vinayak Tantia, Nicolas Ballas and Michael Rabbat
arXiv preprint arXiv:1910.00643
(2019-10-01)
ui.adsabs.harvard.eduPDF

2019-06

Improved Bounds for Max Consensus in Wireless Networks
Aida Nowzari and Michael G. Rabbat
SIPN 2019
(2019-06-01)
ieeexplore.ieee.org
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
Mahmoud Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau and Michael Rabbat

2019-05

Stochastic Gradient Push for Distributed Deep Learning
Mahmoud Assran, Nicolas Loizou, Nicolas Ballas and Michael G. Rabbat
TarMAC: Targeted Multi-Agent Communication
Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Michael G. Rabbat and Joelle Pineau
Provably Accelerated Randomized Gossip Algorithms
Nicolas Loizou, Michael Rabbat and Peter Richtarik
ICASSP 2019
(2019-05-12)
ui.adsabs.harvard.eduPDF
Learning Graphs From Data: A Signal Representation Perspective
Xiaowen Dong, Dorina Thanou, Michael Rabbat and Pascal Frossard
IEEE Signal Processing Magazine
(2019-05-06)
doi.org
Learning Graphs From Data: A Signal Representation Perspective
Xiaowen Dong, Dorina Thanou, Michael Rabbat and Pascal Frossard
IEEE Signal Processing Magazine
(2019-05-06)
doi.orgPDF

2019-01

Graph-Based Compression for Distributed Particle Filters
Jun Ye Yu, Mark J. Coates and Michael G. Rabbat
SIPN 2019
(2019-01-01)
ieeexplore.ieee.org
Uncertainty Principle on Graphs
Bastien Pasdeloup, Vincent Gripon, Réda Alami and Michael G. Rabbat
(venue unknown)
(2019-01-01)
link.springer.com

2018-12

Effectiveness of Alter Sampling in Social Networks.
Naghmeh Momeni and Michael G. Rabbat
arXiv: Social and Information Networks
(2018-12-07)
ui.adsabs.harvard.eduPDF

2018-11

A Graph-CNN for 3D Point Cloud Classification
Yingxue Zhang and Michael Rabbat
arXiv preprint arXiv:1812.01711
(2018-11-28)
ui.adsabs.harvard.eduPDF
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI.
Jure Zbontar, Florian Knoll, Anuroop Sriram, Matthew J. Muckley, Mary Bruno, Aaron Defazio, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael G. Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C. Lawrence Zitnick... (3 more)
arXiv preprint arXiv:1811.08839
(2018-11-21)
ui.adsabs.harvard.eduPDF

Publications collected and formatted using Paperoni