Sotabase

Career

· Research Scientist, Microsoft Research Montreal2021–
· Adjunct Professor, University of Montreal2020–
· Research Scientist, Google Brain Montreal2017–2021
· Adjunct Professor, McGill University2017–
· Research Lead, Criteo2012–2017
· Postdoctoral Researcher, Inria / Ecole Normale Supérieure de Paris2010–2012
· Postdoctoral Researcher, Microsoft Research2008–2010
· PhD in Machine Learning, University of Montreal2004–2008
· MSc. in Mathematics, Vision and Learning, ENS Cachan2002–2003
· MSc. in Applied Mathematics, Ecole Centrale Paris2000–2003

Publications (158)

Minimizing finite sums with the stochastic average gradient
Mathematical programming · 2013
1,309
cited
Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering
Neural Information Processing Systems · 2003
1,150
cited
A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets
Neural Information Processing Systems · 2012
863
cited
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
Neural Computation · 2008
807
cited
Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
Neural Information Processing Systems · 2011
611
cited
A latent factor model for highly multi-relational data
Neural Information Processing Systems · 2012
432
cited
Learning Eigenfunctions Links Spectral Embedding and Kernel PCA
Neural Computation · 2004
339
cited
Ask the locals: Multi-way local pooling for image recognition
Vision · 2011
303
cited
Understanding the impact of entropy on policy optimization
International Conference on Machine Learning · 2018
291
cited
The Curse of Highly Variable Functions for Local Kernel Machines
Neural Information Processing Systems · 2005
237
cited
Topmoumoute Online Natural Gradient Algorithm
Neural Information Processing Systems · 2007
220
cited
Convex Neural Networks
Neural Information Processing Systems · 2005
218
cited
Efficient Non-Parametric Function Induction in Semi-Supervised Learning
International Conference on Artificial Intelligence and Statistics · 2004
207
cited
Deep Belief Networks Are Compact Universal Approximators
Neural Computation · 2010
172
cited
Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition
2013
160
cited
A Stochastic Gradient Method with an Exponential Convergence Rate for Strongly-Convex Optimization with Finite Training Sets
arXiv.org · 2012
104
cited
Learning a Generative Model of Images by Factoring Appearance and Shape
Neural Computation · 2011
104
cited
A Geometric Perspective on Optimal Representations for Reinforcement Learning
Neural Information Processing Systems · 2019
94
cited
On the interplay between noise and curvature and its effect on optimization and generalization
International Conference on Artificial Intelligence and Statistics · 2019
68
cited
Continuous Neural Networks
International Conference on Artificial Intelligence and Statistics · 2007
64
cited
Sotabase