Mila > Team > Pascal Vincent

Pascal Vincent

Core Industry Member
Associate Professor, Université de Montréal, Facebook

My research interests are centered around discovering fundamental computational principles that underlie the extraordinary capabilities to learn from the environment, understand it and adapt to it that characterize intelligence. The development of novel machine learning algorithms based on such principles, and trained on very large data sets, is at the heart of the latest technological breakthroughs in artificial intelligence.

More specifically, I research how higher level representations that carry meaning can be constructed autonomously, starting from streams of raw sensory input (such as images and sounds). Similarly to what our brain’s neural networks naturally know how to do, this amounts to intelligently modeling the structure of the observed reality, by discovering and exploiting hidden and complex statistical regularities that it follows.

Publications

2021-10

Understanding Dimensional Collapse in Contrastive Self-supervised Learning
Li Jing, Pascal Vincent, Yann LeCun and Yuandong Tian
arXiv preprint arXiv:2110.09348
(2021-10-18)
dblp.uni-trier.dePDF

2021-05

Conditional Networks
Anthony Ortiz, Kris Sankaran, Olac Fuentes, Christopher Kiekintveld, Pascal Vincent, Yoshua Bengio and Doina Precup
(venue unknown)
(2021-05-04)
openreview.net
Revisiting Loss Modelling for Unstructured Pruning
César Laurent, Camille Ballas, Thomas George, Pascal Vincent and Nicolas Ballas
arXiv e-prints
(2021-05-04)
ui.adsabs.harvard.eduPDF

2021-03

Implicit Regularization via Neural Feature Alignment
Aristide Baratin, Thomas George, César Laurent, R Devon Hjelm, Guillaume Lajoie, Pascal Vincent and Simon Lacoste-Julien
Accounting for Variance in Machine Learning Benchmarks
Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi, Assya Trofimov, Brennan Nichyporuk, Justin Szeto, Naz Sepah, Edward Raff, Kanika Madan, Vikram Voleti, Samira Ebrahimi Kahou, Vincent Michalski, Dmitriy Serdyuk, Tal Arbel, Chris Pal, Gaël Varoquaux and Pascal Vincent
MLsys 2021 - 4th Conference on Machine Learning and Systems
(2021-03-15)
proceedings.mlsys.orgPDF[Also on arXiv preprint arXiv:2103.03098 (2021-03-01)]
Online Adversarial Attacks.
Andjela Mladenovic, Avishek Joey Bose, Hugo Berard, William L. Hamilton, Simon Lacoste-Julien, Pascal Vincent and Gauthier Gidel
arXiv preprint arXiv:2103.02014
(2021-03-02)
ui.adsabs.harvard.eduPDF

2020-11

Do sequence-to-sequence VAEs learn global features of sentences?
Tom Bosc and Pascal Vincent

2020-10

Efficient Learning in Non-Stationary Linear Markov Decision Processes.
Ahmed Touati and Pascal Vincent
arXiv preprint arXiv:2010.12870
(2020-10-24)
ui.adsabs.harvard.eduPDF

2020-08

Stable Policy Optimization via Off-Policy Divergence Regularization.
Ahmed Touati, Amy Zhang, Joelle Pineau and Pascal Vincent
Implicit Regularization in Deep Learning: A View from Function Space.
Aristide Baratin, Thomas George, César Laurent, R. Devon Hjelm, Guillaume Lajoie, Pascal Vincent and Simon Lacoste-Julien
(venue unknown)
(2020-08-03)
www.microsoft.com

2020-07

Stochastic Hamiltonian Gradient Methods for Smooth Games
Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien and Ioannis Mitliagkas
SVRG for Policy Evaluation with Fewer Gradient Evaluations
Zilun Peng, Ahmed Touati, Pascal Vincent and Doina Precup
Sharp Analysis of Smoothed Bellman Error Embedding.
Ahmed Touati and Pascal Vincent
arXiv preprint arXiv:2007.03749
(2020-07-07)
ui.adsabs.harvard.eduPDF
Adversarial Example Games.
Avishek Joey Bose, Gauthier Gidel, Hugo Berard, Andre Cianflone, Pascal Vincent, Simon Lacoste-Julien and William L. Hamilton
arXiv preprint arXiv:2007.00720
(2020-07-01)
ui.adsabs.harvard.eduPDF

2020-04

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Hugo Berard, Gauthier Gidel, Amjad Almahairi, Pascal Vincent and Simon Lacoste-Julien

2020-01

fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning.
Florian Knoll, Jure Zbontar, Anuroop Sriram, Matthew J Muckley, Mary Bruno, Aaron Defazio, Marc Parente, Krzysztof J Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzalv, Adriana Romero, Michael Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C Lawrence Zitnick... (3 more)
Radiology. Artificial intelligence
(2020-01-29)
europepmc.orgPDF
Adversarial Example Games
Joey Bose, Gauthier Gidel, Hugo Berard, Andre Cianflone, Pascal Vincent, Simon Lacoste-Julien and Will Hamilton
NEURIPS 2020
(2020-01-01)
papers.nips.ccPDF

2019-07

An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation.
Vincent Michalski, Vikram Voleti, Samira Ebrahimi Kahou, Anthony Ortiz, Pascal Vincent, Chris Pal and Doina Precup
arXiv: Computer Vision and Pattern Recognition
(2019-07-31)
ui.adsabs.harvard.eduPDF

2019-05

Unreproducible Research is Reproducible
Xavier Bouthillier, César Laurent and Pascal Vincent
ICML 2019
(2019-05-24)
proceedings.mlr.pressPDF

2019-02

Reducing Uncertainty in Undersampled MRI Reconstruction With Active Acquisition
Zizhao Zhang, Adriana Romero, Matthew J. Muckley, Pascal Vincent, Lin Yang and Michal Drozdzal

2019-01

Stochastic Neural Network with Kronecker Flow.
Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste and Aaron C. Courville

2018-11

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI.
Jure Zbontar, Florian Knoll, Anuroop Sriram, Matthew J. Muckley, Mary Bruno, Aaron Defazio, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael G. Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C. Lawrence Zitnick... (3 more)
arXiv preprint arXiv:1811.08839
(2018-11-21)
ui.adsabs.harvard.eduPDF

2018-07

Convergent Tree Backup and Retrace with Function Approximation
ICML 2018
(2018-07-03)
proceedings.mlr.pressPDF

2018-06

Randomized Value Functions via Multiplicative Normalizing Flows
Ahmed Touati, Harsh Satija, Joshua Romoff, Joelle Pineau and Pascal Vincent
Improving Landmark Localization with Semi-Supervised Learning
Sina Honari, Pavlo Molchanov, Stephen Tyree, Pascal Vincent, Christopher Pal and Jan Kautz
CVPR 2018
(2018-06-01)
www.computer.orgPDF

2018-04

Iteratively unveiling new regions of interest in Deep Learning models
Florian Bordes, Tess Berthier, Lisa Di Jorio, Pascal Vincent and Yoshua Bengio
(venue unknown)
(2018-04-11)
openreview.netPDF

2018-02

A Variational Inequality Perspective on Generative Adversarial Networks
Gauthier Gidel, Hugo Berard, Gaëtan Vignoud, Pascal Vincent and Simon Lacoste-Julien
An Evaluation of Fisher Approximations Beyond Kronecker Factorization
César Laurent, Thomas George, Xavier Bouthillier, Nicolas Ballas and Pascal Vincent
ICLR 2018
(2018-02-12)
dblp.uni-trier.dePDF
Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
Gabriel Huang, Hugo Berard, Ahmed Touati, Gauthier Gidel, Pascal Vincent and Simon Lacoste-Julien
ICLR 2018
(2018-02-01)
ui.adsabs.harvard.eduPDF

2018-01

Auto-Encoding Dictionary Definitions into Consistent Word Embeddings
Tom Bosc and Pascal Vincent
EMNLP 2018
(2018-01-01)
aclanthology.orgPDF
Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
Thomas George, César Laurent, Xavier Bouthillier, Nicolas Ballas and Pascal Vincent

Publications collected and formatted using Paperoni