Pascal Germain, Researcher in Machine Learning

This page is deprecated! My new webage is here.


Journal Papers

Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm
Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand and Jean-Francis Roy
Journal of Machine Learning Research (JMLR), 2015.
[ pdf, bib, abstract ] [ source code, poster ]

Conference Papers

PAC-Bayesian Theory for Transductive Learning
Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy
International Conference on Artificial Intelligence and Statistics (AISTATS), 2014.
[ pdf, supplementary, abstract ] [ poster ] [ source code ]

A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
International Conference on Machine Learning (ICML), 2013.
[ pdf ] [ bib ] [ abstract ] [ supplementary material ] [ source code ]

A Pseudo-Boolean Set Covering Machine
Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, and Claude-Guy Quimper.
International Conference on Principles and Practice of Constraint Programming (CP), 2012.
[ pdf ] [ bib ]

A PAC-Bayes Sample Compression Approach to Kernel Methods
Pascal Germain, Alexandre Lacoste, Francois Laviolette, Mario Marchand and Sara Shanian.
International Conference on Machine Learning (ICML), 2011.
[ pdf ] [ bib ] [ abstract ] [ supplementary material ] [ source code ]

From PAC-Bayes Bounds to KL Regularization
Pascal Germain, Alexandre Lacasse, Francois Laviolette, Mario Marchand, and Sara Shanian.
Advances in Neural Information Processing Systems (NIPS), 2009.
[ pdf ] [ bib ] [ abstract ]

PAC-Bayesian Learning of Linear Classifiers
Pascal Germain, Alexandre Lacasse, Francois Laviolette, and Mario Marchand.
International Conference on Machine Learning (ICML), 2009.
[ pdf ] [ bib ] [ abstract ] [ videolecture ]

A PAC-Bayes risk bound for general loss functions
Pascal Germain, Alexandre Lacasse, Francois Laviolette, and Mario Marchand.
Advances in Neural Information Processing Systems (NIPS), 2007.
[ pdf ] [ bib ] [ abstract ]

PAC-Bayes bounds for the risk of the majority vote and the variance of the gibbs classifier
Alexandre Lacasse, Francois Laviolette, Mario Marchand, Pascal Germain, and Nicolas Usunier.
Advances in Neural Information Processing Systems (NIPS), 2007.
[ pdf ] [ bib ] [ abstract ]

Thesis

Généralisations de la théorie PAC-bayésienne pour l’apprentissage inductif, l’apprentissage transductif et l’adaptation de domaine
Pascal Germain. Ph.D. Thesis, Université Laval, 2015.
[ pdf (french) ] [ slides (french) ]

Master's Thesis

Algorithmes d'apprentissage automatique inspirés de la théorie PAC-Bayes
Pascal Germain. Master's thesis, Université Laval, 2009.
[ pdf (french) ] [ bib ] [ french abstract ] [ english abstract ]


NB : Please visit the GRAAL's publication page to see a list of our research group publications.