Postdoctoral Researcher in Machine Learning

SIERRA Team -- Département d'informatique de l'Ecole Normale Supérieure
Centre de recherche Inria de Paris
2 rue Simone Iff, 75012, Paris, France
E-mail: firstname.lastname@inria.fr

Short academic story : I am studying machine learning problems since few years now. I first joined the GRAAL research group (Université Laval, Quebec City) as an undergraduate research assistant (2006), pursued as a master (2007-2009) and PhD (2009-2015) student, under the supervision of Francois Laviolette and Mario Marchand. In November 2015, I began a postdoc with Francis Bach and the SIERRA Team.

Research interests: Learning theory, learning algorithms, kernel methods, domain adaptation, ...

More about me (elsewhere) : Twitter, Linkedin, GitHub, Google Scholar, dblp, arXiv


Publications

Journal Papers
Domain-Adversarial Training of Neural Networks [ pdf ] [ bib ] [ source code: shallow version | deep version ]
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky (JMLR 2016)

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

Conference Papers
PAC-Bayesian Theory Meets Bayesian Inference [ paper ] [ spotlight: video | slides ] [ poster ] [ code ]
Pascal Germain, Francis Bach, Alexandre Lacoste, Simon Lacoste-Julien (NIPS 2016)

A New PAC-Bayesian Perspective on Domain Adaptation [ pdf ] [ supplemental ] [ bib ] [ source code ]
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant (ICML 2016)

PAC-Bayesian Bounds based on the Rényi Divergence [ paper ] [ bib ] [ poster ]
Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy (AISTATS 2016)

PAC-Bayesian Theory for Transductive Learning [ paper, supplemental ] [ bib ] [ poster ] [ source code ]
Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy (AISTATS 2014)

A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers [ paper, supplemental ] [ bib ] [ source code ] [ extended version ]
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant (ICML 2013)

A Pseudo-Boolean Set Covering Machine [ pdf ]
Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, and Claude-Guy Quimper (CP 2012)

A PAC-Bayes Sample Compression Approach to Kernel Methods [ paper ] [ supplemental ]
Pascal Germain, Alexandre Lacoste, Francois Laviolette, Mario Marchand, and Sara Shanian (ICML 2011)

From PAC-Bayes Bounds to KL Regularization [ pdf ]
Pascal Germain, Alexandre Lacasse, Francois Laviolette, Mario Marchand, and Sara Shanian (NIPS 2009)

PAC-Bayesian Learning of Linear Classifier [ pdf ]
Pascal Germain, Alexandre Lacasse, Francois Laviolette, and Mario Marchand (ICML 2009)

A PAC-Bayes Risk Bound for General Loss Functions [ pdf ]
Pascal Germain, Alexandre Lacasse, Francois Laviolette, and Mario Marchand (NIPS 2006)

PAC-Bayes Bounds for the Risk of the Majority Vote and the Variance of the Gibbs Classifier [ pdf ]
Alexandre Lacasse, Francois Laviolette, Mario Marchand, Pascal Germain, and Nicolas Usunier (NIPS 2006)

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

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

Talks

English Talks
20/06/2016 : A New PAC-Bayesian Perspective on Domain Adaptation [ slides ]
ICML (New-York, US)

02/06/2016 : Variations on the PAC-Bayesian Bound [ slides ]
Bayes in Paris (École nationale de la statistique et de l'administration économique - ENSAE, Paris, France)

31/03/2016 : A Representation Learning Approach for Domain Adaptation [ slides ] [ Proof by Twitter ]
Data Intelligence Group Seminar (Laboratoire Hubert-Curien / Université Jean-Monnet, St-Étienne, France)

01/03/2016 : A Representation Learning Approach for Domain Adaptation [ slides ]
TAO Seminars (INRIA Saclay / CNRS / Université Paris-Sud, Orsay, France)

25/11/2015 : PAC-Bayesian Theory and Domain Adaptation Algorithms [ slides ]
SIERRA Seminars (INRIA Paris / CNRS / ENS, Paris, France)

13/12/2014 : Domain-Adversarial Neural Networks [ slides ] [ workshop paper ]
NIPS 2014 Workshop on Transfer and Multi-task learning: Theory Meets Practice (Montreal, Quebec, Canada)

07/12/2012 : PAC-Bayesian Learning and Domain Adaptation [ slides ]
NIPS 2012 Workshop: Multi-trade-off in Machine Learning (Lake Tahoe, Nevada, US)

09/10/2012 : A Pseudo-Boolean Set Covering Machine [ slides ]
18th International Conference on Principles and Practice of Constraint Programming (Quebec city, Quebec, Canada)

22/03/2010 : Pac-Bayes, Sample Compress & Kernel Methods [ slides ]
Foundations and New Trends of PAC Bayesian Learning Workshop (London, UK)

18/02/2010 : A Sample Compressed SVM [ slides ]
Centre for Computational Statistics and Machine Learning Seminars (London, UK)

French Talks
12/07/2016 : Variations sur la borne PAC-bayésienne [ slides ]
Séminaires du département d'informatique et de génie logiciel (Université Laval, Quebec, Canada)

23/01/2015 : Un réseau de neurones pour l'adaptation de domaine [ slides ]
Séminaires du département d'informatique et de génie logiciel (Université Laval, Quebec, Canada)

05/04/2013 : L'adaptation de domaine en apprentissage automatique: introduction et approche PAC-Bayésienne [ slides ]
Séminaires du département d'informatique et de génie logiciel (Université Laval, Quebec, Canada)

03/04/2009 : Rudiments de l'apprentissage automatique et de la classification (ainsi que quelques notions plus avancées!) [ slides ]
Séminaires de l'Association des étudiant(e)s gradué(e)s en informatique à Laval (Université Laval, Québec, Canada)


Code

Machine Learning Algorithms
PAC-Bayesian Bounds Computation