| Minimizing finite sums with the stochastic average gradient M Schmidt, N Le Roux, F Bach Mathematical Programming 162 (1-2), 83-112, 2017 | 1627 | 2017 |
| Out-of-sample extensions for lle, isomap, mds, eigenmaps, and spectral clustering Y Bengio, JF Paiement, P Vincent, O Delalleau, N Le Roux, M Ouimet NIPS 16, 177-184, 2004 | 1494 | 2004 |
| A stochastic gradient method with an exponential convergence rate for finite training sets N Le Roux, M Schmidt, F Bach NIPS, 2663-2671, 2012 | 1168 | 2012 |
| Representational power of restricted Boltzmann machines and deep belief networks N Le Roux, Y Bengio Neural Computation 20 (6), 1631-1649, 2008 | 1107 | 2008 |
| Convergence rates of inexact proximal-gradient methods for convex optimization M Schmidt, N Le Roux, F Bach NIPS, 2011 | 757 | 2011 |
| A latent factor model for highly multi-relational data R Jenatton, N Le Roux, A Bordes, GR Obozinski NIPS, 3167-3175, 2012 | 549 | 2012 |
| Label propagation and quadratic criterion Y Bengio, O Delalleau, N Le Roux Semi-supervised learning, 193-216, 2006 | 476* | 2006 |
| Ask the locals: multi-way local pooling for image recognition YL Boureau, N Le Roux, F Bach, J Ponce, Y LeCun ICCV, 2011 | 395 | 2011 |
| Understanding the impact of entropy on policy optimization Z Ahmed, N Le Roux, M Norouzi, D Schuurmans International Conference on Machine Learning, 151-160, 2019 | 370 | 2019 |
| Learning eigenfunctions links spectral embedding and kernel PCA Y Bengio, O Delalleau, N Le Roux, JF Paiement, P Vincent, M Ouimet Neural Computation 16 (10), 2197-2219, 2004 | 369 | 2004 |
| The curse of highly variable functions for local kernel machines Y Bengio, O Delalleau, N Le Roux NIPS 18, 107, 2006 | 333 | 2006 |
| Convex neural networks Y Bengio, N Le Roux, P Vincent, O Delalleau, P Marcotte NIPS, 123-130, 2005 | 311 | 2005 |
| Efficient Non-Parametric Function Induction in Semi-Supervised Learning. O Delalleau, Y Bengio, N Le Roux International Conference on Artificial Intelligence and Statistics, 2005 | 267 | 2005 |
| Topmoumoute online natural gradient algorithm N Le Roux, PA Manzagol, Y Bengio NIPS, 849–856, 2008 | 259 | 2008 |
| Deep belief networks are compact universal approximators N Le Roux, Y Bengio Neural computation 22 (8), 2192-2207, 2010 | 218 | 2010 |
| Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition M Schmidt, N Le Roux arXiv preprint arXiv:1308.6370, 2013 | 200 | 2013 |
| The curse of dimensionality for local kernel machines Y Bengio, O Delalleau, N Le Roux Techn. Rep 1258 (12), 1, 2005 | 136 | 2005 |
| A Geometric Perspective on Optimal Representations for Reinforcement Learning MG Bellemare, W Dabney, R Dadashi, AA Taiga, PS Castro, N Le Roux, ... NeurIPS, 2019 | 119 | 2019 |
| Learning a generative model of images by factoring appearance and shape N Le Roux, N Heess, J Shotton, J Winn Neural Computation 23 (3), 593-650, 2011 | 119 | 2011 |
| Spectral clustering and kernel PCA are learning eigenfunctions Y Bengio, P Vincent, JF Paiement, O Delalleau, M Ouimet, N Le Roux CIRANO, 2003 | 92 | 2003 |
Yoshua BengioProfessor of computer science, University of Montreal, Mila, IVADO, CIFARVerified email at umontreal.ca
