Simon Lacoste-Julien

Core Academic Member
Simon Lacoste-Julien
Associate Professor, Université de Montréal, Samsung
Simon Lacoste-Julien

Simon Lacoste-Julien is a an associate professor at Mila and DIRO from Université de Montréal, and Canada CIFAR AI Chair holder. He also heads part time the SAIT AI Lab Montreal. His research interests are machine learning and applied math, with applications to computer vision and natural language processing. He obtained a B.Sc. in math., physics and computer science from McGill, a PhD in computer science from UC Berkeley and a post-doc from the University of Cambridge. He spent a few years as a research faculty at INRIA and École normale supérieure in Paris before coming back to his roots in Montreal in 2016 to answer the call from Yoshua Bengio in growing the Montreal AI ecosystem.

Publications

2020-11

Geometry-Aware Universal Mirror-Prox.
Reza Babanezhad and Simon Lacoste-Julien
arXiv preprint arXiv:2011.11203
(2020-11-23)
dblp.uni-trier.dePDF
On the Convergence of Continuous Constrained Optimization for Structure Learning.
Ignavier Ng, Sébastien Lachapelle, Nan Rosemary Ke and Simon Lacoste-Julien
arXiv preprint arXiv:2011.11150
(2020-11-23)
ui.adsabs.harvard.eduPDF
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets.
Thomas Kerdreux, Lewis Liu, Simon Lacoste-Julien and Damien Scieur
arXiv: Optimization and Control
(2020-11-08)
arxiv.orgPDF

2020-09

Flight-connection Prediction for Airline Crew Scheduling to Construct Initial Clusters for OR Optimizer.
Yassine Yaakoubi, Simon Lacoste-Julien and François Soumis
arXiv: Learning
(2020-09-28)
arxiv.orgPDF
Machine learning in airline crew pairing to construct initial clusters for dynamic constraint aggregation
Yassine Yaakoubi, François Soumis and Simon Lacoste-Julien
EURO Journal on Transportation and Logistics
(2020-09-02)
www.sciencedirect.comPDF
Machine Learning in Airline Crew Pairing to Construct Initial Clusters for Dynamic Constraint Aggregation
Yassine Yaakoubi, François Soumis and Simon Lacoste-Julien
EURO Journal on Transportation and Logistics
(2020-09-01)
api.elsevier.com

2020-08

Implicit Regularization via Neural Feature Alignment.
Aristide Baratin, Thomas George, César Laurent, R Devon Hjelm, Guillaume Lajoie, Pascal Vincent and Simon Lacoste-Julien
arXiv: Learning
(2020-08-03)
arxiv.orgPDF
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
arXiv preprint arXiv:2008.00938
(2020-08-03)
www.microsoft.comPDF

2020-07

Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time.
arXiv: Learning
(2020-07-27)
Stochastic Hamiltonian Gradient Methods for Smooth Games
Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien and Ioannis Mitliagkas
Differentiable Causal Discovery from Interventional Data.
Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien and Alexandre Drouin
arXiv preprint arXiv:2007.01754
(2020-07-03)
dblp.uni-trier.dePDF
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)
dblp.uni-trier.dePDF

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
Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search).
Sharan Vaswani, Frederik Kunstner, Issam H. Laradji, Si Yi Meng, Mark Schmidt and Simon Lacoste-Julien
arXiv preprint arXiv:2006.06835
(2020-06-11)
dblp.uni-trier.dePDF
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation.
Si Yi Meng, Sharan Vaswani, Issam Hadj Laradji, Mark Schmidt and Simon Lacoste-Julien

2020-05

An Analysis of the Adaptation Speed of Causal Models
Rémi Le Priol, Reza Babanezhad Harikandeh, Yoshua Bengio and Simon Lacoste-Julien
arXiv preprint arXiv:2005.09136
(2020-05-18)
dblp.uni-trier.dePDF

2020-04

Gradient-Based Neural DAG Learning
Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu and Simon Lacoste-Julien
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Hugo Berard, Gauthier Gidel, Amjad Almahairi, Pascal Vincent and Simon Lacoste-Julien

2020-02

Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence.
Nicolas Loizou, Sharan Vaswani, Issam H. Laradji and Simon Lacoste-Julien
arXiv preprint arXiv:2002.10542
(2020-02-24)
dblp.uni-trier.dePDF
Machine learning in airline crew pairing to construct initial clusters for dynamic constraint aggregation
François Soumis, Yassine Yaakoubi and Simon Lacoste-Julien
Les Cahiers du GERAD
(2020-02-01)
www.gerad.ca

2020-01

Differentiable Causal Discovery from Interventional Data
Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien and Alexandre Drouin
NEURIPS 2020
(2020-01-01)
papers.nips.cc
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.cc
GAIT: A Geometric Approach to Information Theory.
Jose Gallego-Posada, Ankit Vani, Max Schwarzer and Simon Lacoste-Julien
AISTATS 2020
(2020-01-01)
dblp.uni-trier.de
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games.
AISTATS 2020
(2020-01-01)
proceedings.mlr.press
Accelerating Smooth Games by Manipulating Spectral Shapes.
Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien and Gauthier Gidel

2019-12

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Sharan Vaswani, Aaron Mishkin, Issam Laradji, Mark Schmidt, Gauthier Gidel and Simon Lacoste-Julien
Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks
NEURIPS 2019
(2019-12-08)
papers.nips.ccPDF
Reducing Noise in GAN Training with Variance Reduced Extragradient
Tatjana Chavdarova, Gauthier Gidel, François Fleuret and Simon Lacoste-Julien

2019-09

Are Few-shot Learning Benchmarks Too Simple ?
arXiv: Learning
(2019-09-25)
openreview.netPDF
Scattering Networks for Hybrid Representation Learning
Edouard Oyallon, Sergey Zagoruyko, Gabriel Huang, Nikos Komodakis, Simon Lacoste-Julien, Matthew Blaschko and Eugene Belilovsky
IEEE Transactions on Pattern Analysis and Machine Intelligence
(2019-09-01)
europepmc.orgPDF

2019-06

GEAR: Geometry-Aware Rényi Information.
Jose Gallego-Posada, Ankit Vani, Max Schwarzer and Simon Lacoste-Julien
arXiv: Learning
(2019-06-19)
dblp.uni-trier.dePDF
GAIT: A Geometric Approach to Information Theory
Jose Gallego, Ankit Vani, Max Schwarzer and Simon Lacoste-Julien
arXiv preprint arXiv:1906.08325
(2019-06-19)
arxiv.org
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games
arXiv preprint arXiv:1906.05945
(2019-06-13)
aps.arxiv.org
A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games.
arXiv: Learning
(2019-06-13)
dblp.uni-trier.dePDF

2019-05

A Variational Inequality Perspective on Generative Adversarial Networks
Gauthier Gidel, Hugo Berard, Gaëtan Vignoud, Pascal Vincent and Simon Lacoste-Julien
ICLR 2019
(2019-05-06)
iclr.ccPDF

2019-04

Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks.
arXiv preprint arXiv:1904.13262
(2019-04-30)
arxiv.orgPDF
Negative Momentum for Improved Game Dynamics
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Gabriel Huang, Rémi Le Priol, Simon Lacoste-Julien and Ioannis Mitliagkas
AISTATS 2019
(2019-04-11)
proceedings.mlr.pressPDF
Flight-connection prediction for airline crew scheduling to construct initial clusters for OR optimizer
François Soumis, Yassine Yaakoubi and Simon Lacoste-Julien
Les Cahiers du GERAD
(2019-04-01)
www.gerad.ca

2019-02

Centroid Networks for Few-Shot Clustering and Unsupervised Few-Shot Classification.
arXiv preprint arXiv:1902.08605
(2019-02-22)
dblp.uni-trier.dePDF

2018-12

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates
Kirill Struminsky, Simon Lacoste-Julien and Anton Osokin

2018-09

A Modern Take on the Bias-Variance Tradeoff in Neural Networks
Brady Neal, Sarthak Mittal, Aristide Baratin, Vinayak Tantia, Matthew Scicluna, Simon Lacoste-Julien and Ioannis Mitliagkas
arXiv preprint arXiv:1810.08591
(2018-09-27)
ui.adsabs.harvard.eduPDF
Learning from Narrated Instruction Videos
Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal, Josef Sivic, Ivan Laptev and Simon Lacoste-Julien
IEEE Transactions on Pattern Analysis and Machine Intelligence
(2018-09-01)
hal.archives-ouvertes.frPDF

2018-08

Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields
Rémi Le Priol, Alexandre Piché and Simon Lacoste-Julien
UAI 2018
(2018-08-06)
auai.orgPDF

2018-07

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Eric Larsen, Sébastien Lachapelle, Yoshua Bengio, Emma Frejinger, Simon Lacoste-Julien and Andrea Lodi
arXiv preprint arXiv:1901.07935
(2018-07-31)
aps.arxiv.orgPDF
Predicting Solution Summaries to Integer Linear Programs under Imperfect Information with Machine Learning.
Eric Larsen, Sébastien Lachapelle, Yoshua Bengio, Emma Frejinger, Simon Lacoste-Julien and Andrea Lodi
arXiv: Learning
(2018-07-31)
dblp.uni-trier.dePDF
Negative Momentum for Improved Game Dynamics.
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Remi Lepriol, Gabriel Huang, Simon Lacoste-Julien and Ioannis Mitliagkas
arXiv preprint arXiv:1807.04740
(2018-07-12)
export.arxiv.orgPDF

2018-03

Frank-Wolfe Splitting via Augmented Lagrangian Method
Gauthier Gidel, Fabian Pedregosa and Simon Lacoste-Julien

2018-02

A Variational Inequality Perspective on Generative Adversarial Nets
arXiv preprint arXiv:1802.10551
(2018-02-28)
export.arxiv.orgPDF
SEARNN: Training RNNs with global-local losses
Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin and Simon Lacoste-Julien
ICLR 2018
(2018-02-15)
hal.inria.frPDF
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
(2018-02-15)
ui.adsabs.harvard.eduPDF

2018-01

A3T: Adversarially Augmented Adversarial Training.
Akram Erraqabi, Aristide Baratin, Yoshua Bengio and Simon Lacoste-Julien
arXiv preprint arXiv:1801.04055
(2018-01-12)
ui.adsabs.harvard.eduPDF
Improved asynchronous parallel optimization analysis for stochastic incremental methods
Rémi Leblond, Fabian Pederegosa and Simon Lacoste-Julien
arXiv preprint arXiv:1801.03749
(2018-01-11)
arxiv.orgPDF
Improved asynchronous parallel optimization analysis for stochastic incremental methods
Rémi Leblond, Fabian Pedregosa and Simon Lacoste-Julien
Journal of Machine Learning Research
(2018-01-01)
jmlr.orgPDF

Publications collected and formatted using Paperoni

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