Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Michael Rabbat

Michael Rabbat

McGill University, Montreal, Canada

A Closer Look at Codistillation for Distributed Training


Oct 06, 2020
Shagun Sodhani, Olivier Delalleau, Mahmoud Assran, Koustuv Sinha, Nicolas Ballas, Michael Rabbat

* Under review 

  Access Paper or Ask Questions

Advances in Asynchronous Parallel and Distributed Optimization


Jun 24, 2020
Mahmoud Assran, Arda Aytekin, Hamid Feyzmahdavian, Mikael Johansson, Michael Rabbat

* 33 pages, 4 figures 

  Access Paper or Ask Questions

Recovering Petaflops in Contrastive Semi-Supervised Learning of Visual Representations


Jun 18, 2020
Mahmoud Assran, Nicolas Ballas, Lluis Castrejon, Michael Rabbat


  Access Paper or Ask Questions

On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings


Feb 27, 2020
Mahmoud Assran, Michael Rabbat


  Access Paper or Ask Questions

Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge


Jan 06, 2020
Florian Knoll, Tullie Murrell, Anuroop Sriram, Nafissa Yakubova, Jure Zbontar, Michael Rabbat, Aaron Defazio, Matthew J. Muckley, Daniel K. Sodickson, C. Lawrence Zitnick, Michael P. Recht


  Access Paper or Ask Questions

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum


Oct 01, 2019
Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Michael Rabbat


  Access Paper or Ask Questions

A Graph-CNN for 3D Point Cloud Classification


Nov 28, 2018
Yingxue Zhang, Michael Rabbat

* Published as a conference paper at ICASSP 2018 

  Access Paper or Ask Questions

Stochastic Gradient Push for Distributed Deep Learning


Nov 27, 2018
Mahmoud Assran, Nicolas Loizou, Nicolas Ballas, Michael Rabbat


  Access Paper or Ask Questions

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI


Nov 21, 2018
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 Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C. Lawrence Zitnick, Michael P. Recht, Daniel K. Sodickson, Yvonne W. Lui

* 29 pages, 8 figures 

  Access Paper or Ask Questions

Provably Accelerated Randomized Gossip Algorithms


Oct 31, 2018
Nicolas Loizou, Michael Rabbat, Peter Richtárik


  Access Paper or Ask Questions

TarMAC: Targeted Multi-Agent Communication


Oct 26, 2018
Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Michael Rabbat, Joelle Pineau

* 10 pages, 4 figures, 4 tables 

  Access Paper or Ask Questions

Learning Graphs from Data: A Signal Representation Perspective


Jun 03, 2018
Xiaowen Dong, Dorina Thanou, Michael Rabbat, Pascal Frossard


  Access Paper or Ask Questions

Memory vectors for similarity search in high-dimensional spaces


Mar 01, 2017
Ahmet Iscen, Teddy Furon, Vincent Gripon, Michael Rabbat, Hervé Jégou

* Accepted to IEEE Transactions on Big Data 

  Access Paper or Ask Questions

Combating Corrupt Messages in Sparse Clustered Associative Memories


Sep 27, 2014
Zhe Yao, Vincent Gripon, Michael Rabbat


  Access Paper or Ask Questions

Storing sequences in binary tournament-based neural networks


Sep 01, 2014
Xiaoran Jiang, Vincent Gripon, Claude Berrou, Michael Rabbat


  Access Paper or Ask Questions

Improving Sparse Associative Memories by Escaping from Bogus Fixed Points


Aug 27, 2013
Zhe Yao, Vincent Gripon, Michael Rabbat

* 12 pages 

  Access Paper or Ask Questions

GANC: Greedy Agglomerative Normalized Cut


May 05, 2011
Seyed Salim Tabatabaei, Mark Coates, Michael Rabbat

* Submitted to Pattern Recognition. 27 pages, 5 figures 

  Access Paper or Ask Questions

Multi-path Probabilistic Available Bandwidth Estimation through Bayesian Active Learning


Jan 06, 2010
Frederic Thouin, Mark Coates, Michael Rabbat


  Access Paper or Ask Questions

Greedy Gossip with Eavesdropping


Sep 09, 2009
Deniz Ustebay, Boris Oreshkin, Mark Coates, Michael Rabbat

* 25 pages, 7 figures 

  Access Paper or Ask Questions