Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre National de la Recherche ScientifiqueFR2k papers
- University of British ColumbiaCA1.9k papers
- McGill UniversityCA1.9k papers
- University of VictoriaCA1.8k papers
- University of California, Santa CruzUS1.7k papers
- Rutherford Appleton LaboratoryGB1.7k papers
- University of ManchesterGB1.7k papers
- Queen Mary University of LondonGB1.7k papers
- University of PisaIT1.6k papers
- University of EdinburghGB1.6k papers
- University of BirminghamGB1.6k papers
- Heidelberg UniversityDE1.6k papers
7 papers · 2 filters
Twin Networks: Matching the Future for Sequence Generation
Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni +3
We propose a simple technique for encouraging generative RNNs to plan ahead. We train a "backward" recurrent network to generate a given sequence in reverse order, and we encourage…
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…
Convergent Tree Backup and Retrace with Function Approximation
Ahmed Touati, Pierre-Luc Bacon, Doina Precup +1
Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunat…
A Robust Adaptive Stochastic Gradient Method for Deep Learning
Caglar Gulcehre, Jose Sotelo, Marcin Moczulski +1
Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The…
Sharp Minima Can Generalize For Deep Nets
Laurent Dinh, Razvan Pascanu, Samy Bengio +1
Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, ex…
On Structured Prediction Theory with Calibrated Convex Surrogate Losses
Anton Osokin, Francis Bach, Simon Lacoste-Julien
We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we con…
Calibrating Energy-based Generative Adversarial Networks
Zihang Dai, Amjad Almahairi, Philip Bachman +2
In this paper, we propose to equip Generative Adversarial Networks with the ability to produce direct energy estimates for samples.Specifically, we propose a flexible adversarial t…