R Devon Hjelm

Implicit Regularization in Deep Learning: A View from Function Space

We approach the problem of implicit regularization in deep learning from...
08/03/2020 ∙ by Aristide Baratin, et al. ∙ 39 ∙ share

read it
Representation Learning with Video Deep InfoMax

Self-supervised learning has made unsupervised pretraining relevant agai...
07/27/2020 ∙ by R Devon Hjelm, et al. ∙ 0 ∙ share

read it
Data-Efficient Reinforcement Learning with Momentum Predictive Representations

While deep reinforcement learning excels at solving tasks where large am...
07/12/2020 ∙ by Max Schwarzer, et al. ∙ 0 ∙ share

read it
Deep Reinforcement and InfoMax Learning

Our work is based on the hypothesis that a model-free agent whose repres...
06/12/2020 ∙ by Bogdan Mazoure, et al. ∙ 0 ∙ share

read it
Object-Centric Image Generation from Layouts

Despite recent impressive results on single-object and single-domain ima...
03/16/2020 ∙ by Tristan Sylvain, et al. ∙ 7 ∙ share

read it
An end-to-end approach for the verification problem: learning the right distance

In this contribution, we augment the metric learning setting by introduc...
02/21/2020 ∙ by João Monteiro, et al. ∙ 4 ∙ share

read it
Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning

Continuous control tasks in reinforcement learning are important because...
09/17/2019 ∙ by Thang Doan, et al. ∙ 15 ∙ share

read it
Unsupervised State Representation Learning in Atari

State representation learning, or the ability to capture latent generati...
06/19/2019 ∙ by Ankesh Anand, et al. ∙ 4 ∙ share

read it
Learning Representations by Maximizing Mutual Information Across Views

We propose an approach to self-supervised representation learning based ...
06/03/2019 ∙ by Philip Bachman, et al. ∙ 0 ∙ share

read it
Batch weight for domain adaptation with mass shift

Unsupervised domain transfer is the task of transferring or translating ...
05/29/2019 ∙ by Mikołaj Bińkowski, et al. ∙ 0 ∙ share

read it
Leveraging exploration in off-policy algorithms via normalizing flows

Exploration is a crucial component for discovering approximately optimal...
05/16/2019 ∙ by Bogdan Mazoure, et al. ∙ 0 ∙ share

read it
Prediction of Progression to Alzheimer`s disease with Deep InfoMax

Arguably, unsupervised learning plays a crucial role in the majority of ...
04/24/2019 ∙ by Alex Fedorov, et al. ∙ 0 ∙ share

read it
Spatio-Temporal Deep Graph Infomax

Spatio-temporal graphs such as traffic networks or gene regulatory syste...
04/12/2019 ∙ by Felix L. Opolka, et al. ∙ 0 ∙ share

read it
Adversarial Mixup Resynthesizers

In this paper, we explore new approaches to combining information encode...
03/07/2019 ∙ by Christopher Beckham, et al. ∙ 12 ∙ share

read it
Deep Graph Infomax

We present Deep Graph Infomax (DGI), a general approach for learning nod...
09/27/2018 ∙ by Petar Veličković, et al. ∙ 4 ∙ share

read it
Learning deep representations by mutual information estimation and maximization

Many popular representation-learning algorithms use training objectives ...
08/20/2018 ∙ by R Devon Hjelm, et al. ∙ 0 ∙ share

read it
Online Adaptative Curriculum Learning for GANs

Generative Adversarial Networks (GANs) can successfully learn a probabil...
07/31/2018 ∙ by Thang Doan, et al. ∙ 20 ∙ share

read it
MINE: Mutual Information Neural Estimation

We argue that the estimation of the mutual information between high dime...
01/12/2018 ∙ by Ishmael Belghazi, et al. ∙ 0 ∙ share

read it
ACtuAL: Actor-Critic Under Adversarial Learning

Generative Adversarial Networks (GANs) are a powerful framework for deep...
11/13/2017 ∙ by Anirudh Goyal, et al. ∙ 0 ∙ share

read it
Variance Regularizing Adversarial Learning

We introduce a novel approach for training adversarial models by replaci...
07/02/2017 ∙ by Karan Grewal, et al. ∙ 0 ∙ share

read it
Boundary-Seeking Generative Adversarial Networks

We introduce a novel approach to training generative adversarial network...
02/27/2017 ∙ by R Devon Hjelm, et al. ∙ 0 ∙ share

read it
Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

Despite the successes in capturing continuous distributions, the applica...
02/26/2017 ∙ by Tong Che, et al. ∙ 0 ∙ share

read it
Recurrent Neural Networks for Spatiotemporal Dynamics of Intrinsic Networks from fMRI Data

Functional magnetic resonance imaging (fMRI) of temporally-coherent bloo...
11/03/2016 ∙ by R Devon Hjelm, et al. ∙ 0 ∙ share

read it
Variational Autoencoders for Feature Detection of Magnetic Resonance Imaging Data

Independent component analysis (ICA), as an approach to the blind source...
03/21/2016 ∙ by R Devon Hjelm, et al. ∙ 0 ∙ share

read it
Iterative Refinement of Approximate Posterior for Training Directed Belief Networks

Variational methods that rely on a recognition network to approximate th...
11/19/2015 ∙ by R Devon Hjelm, et al. ∙ 0 ∙ share

read it

R Devon Hjelm

Featured Co-authors

Yoshua Bengio

Kyunghyun Cho

Aaron Courville

Joelle Pineau

Pietro Liò

Simon Lacoste-Julien

Pascal Vincent

Yangqiu Song

Wenjie Li

Adam Trischler

Christopher Pal

Implicit Regularization in Deep Learning: A View from Function Space

Representation Learning with Video Deep InfoMax

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Deep Reinforcement and InfoMax Learning

Object-Centric Image Generation from Layouts

An end-to-end approach for the verification problem: learning the right distance

Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning

Unsupervised State Representation Learning in Atari

Learning Representations by Maximizing Mutual Information Across Views

Batch weight for domain adaptation with mass shift

Leveraging exploration in off-policy algorithms via normalizing flows

Prediction of Progression to Alzheimer`s disease with Deep InfoMax

Spatio-Temporal Deep Graph Infomax

Adversarial Mixup Resynthesizers

Deep Graph Infomax

Learning deep representations by mutual information estimation and maximization

Online Adaptative Curriculum Learning for GANs

MINE: Mutual Information Neural Estimation

ACtuAL: Actor-Critic Under Adversarial Learning

Variance Regularizing Adversarial Learning

Boundary-Seeking Generative Adversarial Networks

Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

Recurrent Neural Networks for Spatiotemporal Dynamics of Intrinsic Networks from fMRI Data

Variational Autoencoders for Feature Detection of Magnetic Resonance Imaging Data

Iterative Refinement of Approximate Posterior for Training Directed Belief Networks