Nicolas Le Roux

Mila > À propos de Mila > Équipe > Nicolas Le Roux
Membre Industriel Principal
Nicolas Le Roux
Professeur associé, McGill University, Google
Nicolas Le Roux

Je suis un chercheur universitaire spécialisé dans l’apprentissage automatique, la vision par ordinateur, les réseaux de neurones, l’apprentissage en profondeur, l’optimisation, l’apprentissage à grande échelle et la modélisation statistique en général.

Publications

2021-08

A functional mirror ascent view of policy gradient methods with function approximation
Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Mueller, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro and Nicolas Le Roux
arXiv preprint arXiv:2108.05828
(2021-08-12)
aps.arxiv.orgPDF
Impact of Aliasing on Generalization in Deep Convolutional Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders, Nicolas Le Roux and Ross Goroshin
arXiv preprint arXiv:2108.03489
(2021-08-07)
arxiv.orgPDF

2021-07

Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
Wesley Chung, Valentin Thomas, Marlos C. Machado and Nicolas Le Roux

2021-06

On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging.
Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux and Michael I. Jordan
arXiv preprint arXiv:2107.00464
(2021-06-30)
dblp.uni-trier.dePDF

2021-05

Batch Reinforcement Learning Through Continuation Method
Yijie Guo, Shengyu Feng, Nicolas Le Roux, Ed Chi, Honglak Lee and Minmin Chen
ICLR 2021
(2021-05-03)
dblp.uni-trier.dePDF

2021-02

Bridging the Gap Between Adversarial Robustness and Optimization Bias
Fartash Faghri, Cristina Vasconcelos, David J. Fleet, Fabian Pedregosa and Nicolas Le Roux
arXiv: Learning
(2021-02-17)
ui.adsabs.harvard.eduPDF

2020-06

To Each Optimizer a Norm, To Each Norm its Generalization.
Sharan Vaswani, Reza Babanezhad, Jose Gallego, Aaron Mishkin, Simon Lacoste-Julien and Nicolas Le Roux
arXiv preprint arXiv:2006.06821
(2020-06-11)
ui.adsabs.harvard.eduPDF

2020-02

The Geometry of Sign Gradient Descent
Lukas Balles, Fabian Pedregosa and Nicolas Le Roux
arXiv preprint arXiv:2002.08056
(2020-02-19)
ui.adsabs.harvard.eduPDF

2020-01

An operator view of policy gradient methods.
Dibya Ghosh, Marlos C. Machado and Nicolas Le Roux
On the interplay between noise and curvature and its effect on optimization and generalization
Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Manzagol, Yoshua Bengio and Nicolas Le Roux
AISTATS 2020
(2020-01-01)
proceedings.mlr.press

2019-06

On the interplay between noise and curvature and its effect on optimization and generalization
Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Mangazol, Yoshua Bengio and Nicolas Le Roux
arXiv: Learning
(2019-06-18)
ui.adsabs.harvard.eduPDF
Information matrices and generalization
Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Manzagol, Yoshua Bengio and Nicolas Le Roux
(venue unknown)
(2019-06-18)
dblp.uni-trier.dePDF

2019-05

Understanding the impact of entropy on policy optimization
Zafarali Ahmed, Nicolas Le Roux, Mohammad Norouzi and Dale Schuurmans

2019-04

Distributional reinforcement learning with linear function approximation
Marc G. Bellemare, Nicolas Le Roux, Pablo Samuel Castro and Subhodeep Moitra

2019-03

Improving NILM by Combining Sensor Data and Linear Programming
Nicolas Roux, Baptiste Vrigneau and Olivier Sentieys
SAS 2019
(2019-03-01)
dblp.uni-trier.de

2019-02

Anytime Tail Averaging.
arXiv preprint arXiv:1902.05083
(2019-02-13)
ui.adsabs.harvard.eduPDF
Negative eigenvalues of the Hessian in deep neural networks
Guillaume Alain, Nicolas Le Roux and Pierre-Antoine Manzagol
arXiv preprint arXiv:1902.02366
(2019-02-06)
ui.adsabs.harvard.eduPDF

2019-01

The Value Function Polytope in Reinforcement Learning
Robert Dadashi, Adrien Ali Taiga, Nicolas Le Roux, Dale Schuurmans and Marc G. Bellemare
A Geometric Perspective on Optimal Representations for Reinforcement Learning
Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taïga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore and Clare Lyle
Reducing the variance in online optimization by transporting past gradients
Sébastien M. R. Arnold, Pierre-Antoine Manzagol, Reza Babanezhad, Ioannis Mitliagkas and Nicolas Le Roux

2018-11

Understanding the impact of entropy in policy learning
Zafarali Ahmed, Nicolas Le Roux, Mohammad Norouzi and Dale Schuurmans
(venue unknown)
(2018-11-27)
arxiv.org

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "fr" }