1.5k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université de MontréalCA125 papers
- McGill UniversityCA59 papers
- Polytechnique MontréalCA27 papers
- Flatiron Health (United States)US24 papers
- Flatiron Institute23 papers
- Centre National de la Recherche ScientifiqueFR22 papers
- University of TorontoCA16 papers
- Canadian Institute for Advanced ResearchCA14 papers
- Université Paris-SaclayFR14 papers
- University of AmsterdamNL13 papers
- University of WaterlooCA13 papers
- Centre for Research in Astrophysics of QuébecCA12 papers
13 papers · 2 filters
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi +2
A major challenge in reinforcement learning is the design of exploration strategies, especially for environments with sparse reward structures and continuous state and action space…
Geometric Scattering Attention Networks
Yimeng Min, Frederik Wenkel, Guy Wolf
Geometric scattering has recently gained recognition in graph representation learning, and recent work has shown that integrating scattering features in graph convolution networks…
Maximum Reward Formulation In Reinforcement Learning
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall +6
Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several cruc…
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…
NeuMiss networks: differentiable programming for supervised learning with missing values
Marine Le Morvan, Julie Josse, Thomas Moreau +2
The presence of missing values makes supervised learning much more challenging. Indeed, previous work has shown that even when the response is a linear function of the complete dat…
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Sarthak Mittal, Alex Lamb, Anirudh Goyal +5
Robust perception relies on both bottom-up and top-down signals. Bottom-up signals consist of what's directly observed through sensation. Top-down signals consist of beliefs and ex…
PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan +2
Large capacity deep learning models are often prone to a high generalization gap when trained with a limited amount of labeled training data. A recent class of methods to address t…
Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
David Macêdo, Tsang Ing Ren, Cleber Zanchettin +2
In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to pr…
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Yimeng Min, Frederik Wenkel, Guy Wolf
Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features. This gave rise to extensive work in geometric deep…
Out-of-Distribution Generalization via Risk Extrapolation (REx)
David Krueger, Ethan Caballero, Joern-Henrik Jacobsen +5
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that vari…
Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming
Mostafa ElAraby, Guy Wolf, Margarida Carvalho
We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in deep neural network architectures which is guided by the impact of their simultaneous p…
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization
Miloš Nikolić, Ghouthi Boukli Hacene, Ciaran Bannon +5
Neural networks have demonstrably achieved state-of-the art accuracy using low-bitlength integer quantization, yielding both execution time and energy benefits on existing hardware…
Linear predictor on linearly-generated data with missing values: non consistency and solutions
Marine Le Morvan, Nicolas Prost, Julie Josse +2
We consider building predictors when the data have missing values. We study the seemingly-simple case where the target to predict is a linear function of the fully-observed data an…