Gauthier Gidel

Ph.D. Candidate
Université de Montréal - DIRO
Montréal Institute for Learning Algorithms


I am a Ph.D candidate supervised by Simon Lacoste-Julien, I graduated from ENS Ulm and Université Paris-Saclay. I am currently a visiting PhD student at Sierra. I also worked for 6 months as a freelance Data Scientist for Monsieur Drive and Les Suggestions de Nelly. My work focuses on optimization applied to machine learning. More details can be found in my resume.


Research interests


My research is to develop new optimization algorithms and understand to role of optimization in the learning procedure. I identify to the field of machine learning (NIPS,ICML,AISTATS) and optimization (SIAM OP)

Papers


Machine learning and optimization

[NEW!] Frank-Wolfe Splitting via Augmented Lagrangian Method
Gauthier Gidel, Fabian Pedregosa and Simon Lacoste-Julien.
Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.
(ORAL, TOP 5% of submitted papers)

Paper Poster Slides bibtex
@InProceedings{gidel2018fwal,
  author      = {Gidel, Gauthier and Pedregosa, Fabian and Lacoste-Julien, Simon},
  title       = {Frank-Wolfe Splitting via Augmented Lagrangian Method},
  journal     = {AISTATS},
  note        = {to appear},
  year        = {2018} 
}

[NEW!] A Variational Inequality Perspective on Generative Adversarial Nets
Gauthier Gidel, Hugo Berard, Pascal Vincent and Simon Lacoste-Julien.
arXiv, 2018.

bibtex arXiv
@InProceedings{gidel2018variational,
  author      = {Gidel, Gauthier and Berard, Hugo and Vincent, Pascal and Lacoste-Julien, Simon},
  title       = {A Variational Inequality Perspective on Generative Adversarial Nets},
  journal     = {arXiv},
  year        = {2018} 
}

[NEW!] Adaptive Three Operator Splitting
Fabian Pedregosa, Gauthier Gidel.
arXiv, 2018.

bibtex arXiv
@InProceedings{pedregosa2018adaptive,
  author      = {Pedregosa, Fabian and Gidel, Gauthier},
  title       = {Adaptive Three Operator Splitting},
  journal     = {arXiv},
  year        = {2018} 
}

Frank-Wolfe Algorithms for Saddle Point Problems
Gauthier Gidel, Tony Jebara and Simon Lacoste-Julien.
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.

Article bibtex arXiv
@InProceedings{gidel2017saddle,
  author      = {Gidel, Gauthier and Jebara, Tony and Lacoste-Julien, Simon},
  title       = {{F}rank-{W}olfe Algorithms for Saddle Point Problems},
  journal     = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year        = {2017} 
}
HAL Code Project Poster

Generative Modeling

Adversarial Divergences are Good Task Losses for Generative Modeling
Gabriel Huang, Gauthier Gidel, Hugo Berard, Ahmed Touati, Simon Lacoste-Julien.
arXiv, 2017.

Article bibtex arXiv
@InProceedings{huang2017adversarial,
  author    = {Huang, Gabriel and Gidel, Gauthier and Berard, Hugo and Touati Ahmed and Lacoste-Julien, Simon},
  title     = {Adversarial Divergences are Good Task Losses for Generative Modeling},
  journal   = {arXiv:1708.02511},
  year      = {2017} 
}


Talks


Machine learning and optimization

Frank-Wolfe Algorithms for Saddle Point Problems
Gauthier Gidel, Tony Jebara and Simon Lacoste-Julien.


Extensions de l’algorithme de Frank-Wolfe pour la recherche de points selles. (In French)
Gauthier Gidel.
Introduction au domaine de recherche ENS 2016


Review of Improving branch-and-cut performance by random sampling. (In French)
Gauthier Gidel.
Paper review in MIP course of Bernard Gendron, 2017



Workshops


Machine learning and optimization

Frank-Wolfe Splitting via Augmented Lagrangian Method
Gauthier Gidel, Fabian Pedregosa and Simon Lacoste-Julien.
NIPSOPT, 2017.


Frank-Wolfe Algorithms for Saddle Point Problems
Gauthier Gidel, Tony Jebara and Simon Lacoste-Julien.
NIPS OPT workshop (ORAL top 10% accepted submissions), 2016

Extended Abstract bibtex
@InProceedings{gidel2016saddleabstract,
  author      = {Gidel, Gauthier and Jebara, Tony and Lacoste-Julien, Simon},
  title       = {{F}rank-{W}olfe Algorithms for Saddle Point Problems},
  booktitle   = {NIPS OPT workshop},
  year        = {2016} 
}
Slides Poster

Generative Modeling

Adversarial Divergences are Good Task Losses for Generative Modeling
Gabriel Huang, Gauthier Gidel, Hugo Berard, Ahmed Touati, Simon Lacoste-Julien.
Principled Approaches in Deep Learning, 2017.



Teaching Experience


Examiner for oral exams in mathematics


Contact


Gauthier Gidel
Pavillon André-Aisenstadt
2920 Chemin de la Tour, office 3331
Montreal, QC
H3T 1J4 CANADA