1.7k citations · 3.4k across the 31 of their papers we have counts for
18 papers · 1 filter
Value function estimation using conditional diffusion models for control
Bogdan Mazoure, Walter Talbott, Miguel Angel Bautista +3
A fairly reliable trend in deep reinforcement learning is that the performance scales with the number of parameters, provided a complimentary scaling in amount of training data. As…
Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypes
Alex Fedorov, Eloy Geenjaar, Lei Wu +7
Recent neuroimaging studies that focus on predicting brain disorders via modern machine learning approaches commonly include a single modality and rely on supervised over-parameter…
The Sandbox Environment for Generalizable Agent Research (SEGAR)
R Devon Hjelm, Bogdan Mazoure, Florian Golemo +5
A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress. While there…
Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL
Bogdan Mazoure, Ahmed M. Ahmed, Patrick MacAlpine +2
A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks…
Implicit Regularization via Neural Feature Alignment
Aristide Baratin, Thomas George, César Laurent +4
We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induced by a dynamical alignment of the neura…
Data-Efficient Reinforcement Learning with Self-Predictive Representations
Max Schwarzer, Ankesh Anand, Rishab Goel +3
While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from l…
Deep Reinforcement and InfoMax Learning
Bogdan Mazoure, Remi Tachet des Combes, Thang Doan +2
We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving a…
An end-to-end approach for the verification problem: learning the right distance
Joao Monteiro, Isabela Albuquerque, Jahangir Alam +2
In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder. Several interpretations are thus drawn f…
Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
Thang Doan, Bogdan Mazoure, Moloud Abdar +3
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, w…
Learning Representations by Maximizing Mutual Information Across Views
Philip Bachman, R Devon Hjelm, William Buchwalter
We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For exa…
Unsupervised State Representation Learning in Atari
Ankesh Anand, Evan Racah, Sherjil Ozair +3
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of…
Batch weight for domain adaptation with mass shift
Mikołaj Bińkowski, R Devon Hjelm, Aaron Courville
Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain…
Leveraging exploration in off-policy algorithms via normalizing flows
Bogdan Mazoure, Thang Doan, Audrey Durand +2
The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many real-world scenarios. Approaches su…
Prediction of Progression to Alzheimer's disease with Deep InfoMax
Alex Fedorov, R Devon Hjelm, Anees Abrol +4
Arguably, unsupervised learning plays a crucial role in the majority of algorithms for processing brain imaging. A recently introduced unsupervised approach Deep InfoMax (DIM) is a…
Spatio-Temporal Deep Graph Infomax
Felix L. Opolka, Aaron Solomon, Cătălina Cangea +3
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes ove…
On-line Adaptative Curriculum Learning for GANs
Thang Doan, Joao Monteiro, Isabela Albuquerque +4
Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open questions such as sufficient convergence…
MINE: Mutual Information Neural Estimation
Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar +4
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutua…
Variational Autoencoders for Feature Detection of Magnetic Resonance Imaging Data
R. Devon Hjelm, Sergey M. Plis, Vince C. Calhoun
Independent component analysis (ICA), as an approach to the blind source-separation (BSS) problem, has become the de-facto standard in many medical imaging settings. Despite succes…