81 citations
- Université de MontréalCA11 papers
- McGill UniversityCA7 papers
- Google DeepMind (United Kingdom)GB3 papers
- Brain (Germany)DE2 papers
- Flatiron Health (United States)US2 papers
- Flatiron Institute2 papers
- Google (United States)US2 papers
- Peking UniversityCN2 papers
- Samsung (South Korea)KR2 papers
- Tencent (China)CN2 papers
- Ahlia UniversityBH1 paper
- Brown UniversityUS1 paper
7 papers · 1 filter
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
Thomas Kerdreux, Lewis Liu, Simon Lacoste-Julien +1
It is known that the Frank-Wolfe (FW) algorithm, which is affine-covariant, enjoys accelerated convergence rates when the constraint set is strongly convex. However, these results…
Visual Concept Reasoning Networks
Taesup Kim, Sungwoong Kim, Yoshua Bengio
A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connec…
Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal +4
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic…
Stochastic Hamiltonian Gradient Methods for Smooth Games
Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau +3
The success of adversarial formulations in machine learning has brought renewed motivation for smooth games. In this work, we focus on the class of stochastic Hamiltonian methods a…
What can I do here? A Theory of Affordances in Reinforcement Learning
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici +2
Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the feature…
Revisiting Loss Modelling for Unstructured Pruning
César Laurent, Camille Ballas, Thomas George +2
By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. I…