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
4 papers · 2 filters
Parametric Adversarial Divergences are Good Losses for Generative Modeling
Gabriel Huang, Hugo Berard, Ahmed Touati +3
Parametric adversarial divergences, which are a generalization of the losses used to train generative adversarial networks (GANs), have often been described as being approximations…
SEARNN: Training RNNs with Global-Local Losses
Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin +1
We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been wide…
Improved Training of Wasserstein GANs
Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky +2
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stab…
On orthogonality and learning recurrent networks with long term dependencies
Eugene Vorontsov, Chiheb Trabelsi, Samuel Kadoury +1
It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradie…