Pascal Vincent

Pascal Vincent is a Research Scientist at Facebook AI Research (FAIR) in Montreal, as well as an Associate Professor in the Department of Computer Science and Operations Research at Université de Montréal, a founding member of the Montreal Institute for Learning Algorithms (MILA) and Associate Fellow in the Canadian Institute for Advanced Research (CIFAR / Learning Machines and Brains program). Pascal has been conducting research on artificial neural networks since 1995 and completed a PhD in computer-science/machine-learning at Université de Montréal under the direction of Yoshua Bengio in 2004. Pascal's primary research focus is the development of original approaches for representation learning that aim to be both statistically and computationally efficient, in order to enable the learning of more meaningful and practically useful representations across multiple application domains such as vision and language understanding.

Pascal's Publications

May 26, 2020

RESEARCH

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

Generative adversarial networks has been very successful in generative modeling, however they remain relatively challenging to train compared to standard deep neural networks. In this paper, we propose new visualization techniques for the optimization landscapes of GANs that enable us to study the game vector field resulting from the concatenation…

Hugo Berard, Gauthier Gidel, Amjad Almahairi, Pascal Vincent, Simon Lacoste-Julien

May 26, 2020

May 26, 2020

RESEARCH

Randomized Value Functions via Multiplicative Normalizing Flows

Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value functions maintain a posterior distribution over action-space values. This prevents the agent’s behavior policy from…

Ahmed Touati, Harsh Satija, Joshua Romoff, Joelle Pineau, Pascal Vincent

May 26, 2020

May 26, 2020

RESEARCH

Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition

The goal of MRI reconstruction is to restore a high fidelity image from partially observed measurements. This partial view naturally induces reconstruction uncertainty that can only be reduced by acquiring additional measurements. In this paper, we present a novel method for MRI reconstruction that, at inference time, dynamically selects the…

Zizhao Zhang, Adriana Romero, Matthew J. Muckley, Pascal Vincent, Lin Yang, Michal Drozdzal

May 26, 2020