Devon Hjelm

Mila > About Mila > Team > Devon Hjelm
Core Industry Member
Devon Hjelm
Adjunct Professor, Université de Montréal, Microsoft Research
Devon Hjelm

I am a deep learning Researcher at Microsoft Research, Montreal. I received my PhD at the University of New Mexico, where I studied learning representations of the brain using graphical models. I did a postdoc under Yoshua Bengio doing unsupervised learning, representation learning, and adversarial models. At Microsoft, I study how to learn better representations for scientific analysis and downstream tasks in RL and NLP.

Publications

2021-06

Predicting Unreliable Predictions by Shattering a Neural Network
Xu Ji, Razvan Pascanu, R. Devon Hjelm, Andrea Vedaldi, Balaji Lakshminarayanan and Yoshua Bengio
arXiv preprint arXiv:2106.08365
(2021-06-15)
ui.adsabs.harvard.eduPDF
Pretraining Representations for Data-Efficient Reinforcement Learning
Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, R. Devon Hjelm, Philip Bachman and Aaron C. Courville
arXiv preprint arXiv:2106.04799
(2021-06-09)
dblp.uni-trier.dePDF
CMIM: Cross-Modal Information Maximization For Medical Imaging
Tristan Sylvain, Francis Dutil, Tess Berthier, Lisa Di Jorio, Margaux Luck, Devon Hjelm and Yoshua Bengio
ICASSP 2021
(2021-06-06)
ieeexplore.ieee.org
Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL.
Bogdan Mazoure, Ahmed M. Ahmed, Patrick MacAlpine, R. Devon Hjelm and Andrey Kolobov
arXiv preprint arXiv:2106.02193
(2021-06-04)
ui.adsabs.harvard.eduPDF

2021-05

Understanding by Understanding Not: Modeling Negation in Language Models.
Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R. Devon Hjelm, Alessandro Sordoni and Aaron C. Courville
Data-Efficient Reinforcement Learning with Self-Predictive Representations
Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville and Philip Bachman

2021-03

Implicit Regularization via Neural Feature Alignment
Aristide Baratin, Thomas George, César Laurent, R Devon Hjelm, Guillaume Lajoie, Pascal Vincent and Simon Lacoste-Julien
Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning
Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, R Devon Hjelm, Philip Bachman and Aaron Courville
ICLR 2021
(2021-03-09)
openreview.netPDF

2020-12

Deep Reinforcement and InfoMax Learning
Bogdan Mazoure, Remi Tachet des Combes, Thang Long Doan, Philip Bachman and R Devon Hjelm

2020-10

Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations.
Tristan Sylvain, Linda Petrini and R. Devon Hjelm
arXiv preprint arXiv:2010.13320
(2020-10-22)
ui.adsabs.harvard.eduPDF
Cross-Modal Information Maximization for Medical Imaging: CMIM.
Tristan Sylvain, Francis Dutil, Tess Berthier, Lisa Di-Jorio, Margaux Luck, R. Devon Hjelm and Yoshua Bengio
arXiv preprint arXiv:2010.10593
(2020-10-20)
dblp.uni-trier.dePDF

2020-08

Implicit Regularization in Deep Learning: A View from Function Space.
Aristide Baratin, Thomas George, César Laurent, R. Devon Hjelm, Guillaume Lajoie, Pascal Vincent and Simon Lacoste-Julien
(venue unknown)
(2020-08-03)
www.microsoft.com

2020-07

Data-Efficient Reinforcement Learning with Momentum Predictive Representations. (arXiv:2007.05929v2 [cs.LG] UPDATED)
Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville and Philip Bachman
arXiv Computer Science
(2020-07-24)
Data-Efficient Reinforcement Learning with Momentum Predictive Representations
Max Schwarzer, Ankesh Anand, Rishab Goel, R. Devon Hjelm, Aaron C. Courville and Philip Bachman
ICLR 2020
(2020-07-12)
www.microsoft.comPDF
An end-to-end approach for the verification problem: learning the right distance
Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R Devon Hjelm and Tiago Falk

2020-04

Locality and Compositionality in Zero-Shot Learning
Tristan Sylvain, Linda Petrini and Devon Hjelm

2020-03

Object-Centric Image Generation from Layouts.
Tristan Sylvain, Pengchuan Zhang, Yoshua Bengio, R. Devon Hjelm and Shikhar Sharma

2019-12

Unsupervised State Representation Learning in Atari
Ankesh Anand, Evan Racah, Sherjil Ozair, Yoshua Bengio, Marc-Alexandre Côté and R Devon Hjelm

2019-10

Batch Weight for Domain Adaptation With Mass Shift
Mikolaj Binkowski, Devon Hjelm and Aaron Courville
Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction
Alaaeldin El-Nouby, Shikhar Sharma, Hannes Schulz, R Devon Hjelm, Layla El Asri, Samira Ebrahimi Kahou, Yoshua Bengio and Graham Taylor

2019-09

Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
Thang Doan, Bogdan Mazoure, Audrey Durand, Joelle Pineau and R Devon Hjelm
arXiv preprint arXiv:1909.07543
(2019-09-25)
ui.adsabs.harvard.eduPDF

2019-07

On-line Adaptative Curriculum Learning for GANs
Thang Doan, João Monteiro, Isabela Albuquerque, Bogdan Mazoure, Audrey Durand, Joelle Pineau and R. Devon Hjelm

2019-06

Learning Representations by Maximizing Mutual Information Across Views
Philip Bachman, R Devon Hjelm and William Buchwalter

2019-05

Prediction of Progression to Alzheimer's disease with Deep InfoMax
Alex Fedorov, R Devon Hjelm, Anees Abrol, Zening Fu, Yuhui Du, Sergey Plis and Vince D. Calhoun
Leveraging exploration in off-policy algorithms via normalizing flows
Bogdan Mazoure, Thang Doan, Audrey Durand, R Devon Hjelm and Joelle Pineau
arXiv preprint arXiv:1905.06893
(2019-05-16)
ui.adsabs.harvard.eduPDF

2019-04

Spatio-Temporal Deep Graph Infomax.
Felix L. Opolka, Aaron Solomon, Catalina Cangea, Petar Velickovic, Pietro Liò and R. Devon Hjelm
arXiv preprint arXiv:1904.06316
(2019-04-12)
ui.adsabs.harvard.eduPDF

2019-03

Adversarial Mixup Resynthesizers
Christopher Beckham, Sina Honari, Alex Lamb, Vikas Verma, Farnoosh Ghadiri, R. Devon Hjelm and Christopher J. Pal

2019-01

Leveraging exploration in off-policy algorithms via normalizing flows.
Bogdan Mazoure, Thang Doan, Audrey Durand, Joelle Pineau and R. Devon Hjelm
Conference on Robot Learning
(2019-01-01)
proceedings.mlr.pressPDF
On Adversarial Mixup Resynthesis
Christopher Beckham, Sina Honari, Vikas Verma, Alex M. Lamb, Farnoosh Ghadiri, R Devon Hjelm, Yoshua Bengio and Chris Pal

2018-11

Keep Drawing It: Iterative language-based image generation and editing
Alaaeldin El-Nouby, Shikhar Sharma, Hannes Schulz, Devon Hjelm, Layla El Asri, Samira Ebrahimi Kahou, Yoshua Bengio and Graham W. Taylor
NEURIPS 2018
(2018-11-24)
[LATEST on None (2018-11-24)]

2018-09

Unsupervised one-to-many image translation
Samuel Lavoie-Marchildon, Sebastien Lachapelle, Mikołaj Bińkowski, Aaron Courville, Yoshua Bengio and R Devon Hjelm
(venue unknown)
(2018-09-27)
openreview.netPDF
Deep Graph Infomax
Petar Velickovic, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio and R. Devon Hjelm

2018-08

Learning deep representations by mutual information estimation and maximization
R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler and Yoshua Bengio

2018-07

Mutual Information Neural Estimation.
Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville and Devon Hjelm
ICML 2018
(2018-07-03)
proceedings.mlr.pressPDF

2018-06

Mine: mutual information neural estimation
Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville and Devon Hjelm
ICML 2018
(2018-06-07)
www.microsoft.com

2018-02

Learning Generative Models with Locally Disentangled Latent Factors
Brady Neal, Alex Lamb, Sherjil Ozair, Devon Hjelm, Aaron Courville, Yoshua Bengio and Ioannis Mitliagkas
(venue unknown)
(2018-02-15)
openreview.netPDF
Boundary Seeking GANs
R Devon Hjelm, Athul Paul Jacob, Adam Trischler, Gerry Che, Kyunghyun Cho and Yoshua Bengio
ICLR 2018
(2018-02-15)
www.microsoft.comPDF
Variance Regularizing Adversarial Learning
Karan Grewal, R Devon Hjelm and Yoshua Bengio
arXiv preprint arXiv:1707.00309
(2018-02-15)
128.84.21.199PDF

2018-01

MINE: Mutual Information Neural Estimation.
Ishmael Belghazi, Sai Rajeswar, Aristide Baratin, R. Devon Hjelm and Aaron C. Courville
arXiv preprint arXiv:1801.04062
(2018-01-12)
ui.adsabs.harvard.eduPDF

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }