Professeur agrégé en informatique
Associate professor in computer science

Département d’informatique et de génie logiciel, Pavillon Adrien-Pouliot, Local PLT-3949
Université Laval, Québec (QC), Canada, G1V 0A6

Courriel / e-mail: firstname.lastname@ift.ulaval.ca


Chercheur en apprentissage automatique
Machine learning researcher

  • Membre du GRAAL / CRDM / IID
  • Membre académique associé au MILA -- Associate academic member at MILA

Intérêts de recherche / Research interests:
Statistical machine learning theory (with an emphasis on PAC-Bayesian learning), domain adaptation, learning algorithms, representation learning, interpretability ...


Graduate Students and Postdocs

Current
  • Benjamin Leblanc (PhD candidate)
  • Thibaud Godon (PhD candidate, co-supervised by Alexandre Drouin and Jacques Corbeil)
  • Mathieu Bazinet (PhD candidate, co-supervised by Valentina Zantedeschi)
  • Élina Francovic-Fontaine (PhD candidate, co-supervised with Jacques Corbeil)
  • Sandrine Blais-Deschênes (PhD candidate, co-supervised with Josée Desharnais)
  • Simon Bertrand (PhD candidate, co-supervised with Nadia Tawbi)
  • Shubham Gupta (PhD candidate, co-supervised with Cem Subakan)
  • Jacob Comeau (MSc candidate, co-supervised with Cem Subakan)
  • Nathaniel D'Amours (MSc candidate, co-supervised by Christian Ethier)
  • Karine Dufresne (PhD candidate, co-supervised by Catherine Ouellet)
Past
  • Sokhna Diarra Mbacke (PhD)
  • Louis-Philippe Vignault (MSc co-supervised with Audrey Durand)
  • Gaël Letarte (PhD co-supervised by François Laviolette)
  • Paul Viallard (PhD co-supervised with Amaury Habrard and Emilie Morvant)
  • Mathieu Alain (MSc co-supervised with François Laviolette)
  • Luxin Zhang (PhD co-supervised with Christophe Biernacki and Yacine Kessaci)
  • Étienne Gael Tajeuna (postdoc co-supervised by Jacques Corbeil)
  • Vera Shalaeva (postdoc)

Publications

See also: dblp, Google Scholar, Semantic Scholar
Selected Reports
Sample Compression for Self Certified Continual LearningarXiv ]
Jacob Comeau, Mathieu Bazinet, Pascal Germain, Cem Subakan (2025)

Invariant Causal Set Covering MachinesarXiv ]
Thibaud Godon, Baptiste Bauvin, Pascal Germain, Jacques Corbeil, Alexandre Drouin (2025)

Peer-Reviewed Works (conference, journals, workshops)
Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression HypernetworksarXiv ]
Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain (ICML 2025)

On Selecting Robust Approaches for Learning Predictive Biomarkers in Metabolomics Data Sets  paper ]
Thibaud Godon, Pier-Luc Plante, Jacques Corbeil, Pascal Germain, Alexandre Drouin (Analytical Chemistry 2025)

Sample Compression Unleashed: New Generalization Bounds for Real Valued LossesarXiv preprint ]
Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain (AISTATS 2025)

Application of machine learning tools to study the synergistic impact of physicochemical properties of peptides and filtration membranes on peptide migration during electrodialysis with filtration membranes  paper ]
Zain Sanchez-Reinoso, Mathieu Bazinet, Benjamin Leblanc, Jean-Pierre Clément, Pascal Germain, Laurent Bazinet (Separation and Purification Technology 2025)

Unsupervised Insider Threat Detection Using Multi-Head Self-Attention Mechanismsproceedings ]
Simon Bertrand, Pascal Germain, Nadia Tawbi (Intelligent Cybersecurity Conference, ICSC 2024)

Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated VoicearXiv preprint ]
Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan (Interspeech 2024)

Seeking Interpretability and Explainability in Binary Activated Neural NetworksarXiv preprint ]
Benjamin Leblanc, Pascal Germain (World Conference on eXplainable Artificial Intelligence, xAI 2024)

A General Framework for the Practical Disintegration of PAC-Bayesian Boundsarticle ] [ arXiv preprint ]
Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant (Mach. Learn. 2024)

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theoryproceedings ] [ arXiv ]
Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain (NeurIPS 2023)

PAC-Bayesian Generalization Bounds for Adversarial Generative Modelsproceedings ] [ arXiv ] [ bibtex ]
Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain (ICML 2023)

Erratum: Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithmpaper ]
Pascal Germain, Audrey Durand, Louis-Philippe Vignault (JMLR 2023)

Sample Boosting Algorithm (SamBA) - An Interpretable Greedy Ensemble Classifier Based On Local Expertise For Fat Dataproceedings ] [ bibtex ]
Baptiste Bauvin, Cécile Capponi, Florence Clerc, Pascal Germain, Sokol Koço, Jacques Corbeil (UAI 2023)

PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representationsproceedings ] [ arXiv ] [ bibtex ]
Louis Fortier-Dubois, Benjamin Leblanc, Gaël Letarte, François Laviolette, Pascal Germain (CANAI 2023)

Interpretable Domain Adaptation Using Unsupervised Feature Selection on Pre-trained Source Modelspaper ] [ preprint ] [ code ]
Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki (Neurocomputing 2022)

Interpretable Domain Adaptation for Hidden Subdomain Alignment in the Context of Pre-Trained Source Modelsproceedings ] [ supplemental ] [ HAL ] [ spotlight ] [ code ]
Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki (AAAI 2022)

Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Boundproceedings ] [ arXiv ]
Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj (NeurIPS 2021)

Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Boundpaper ]
Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant (ECML 2021)

Target to Source Coordinate-wise Adaptation of Pre-trained Modelspaper ] [ supplemental ] [ video ] [ code ]
Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki (ECML 2020)

Landmark-based Ensemble Learning with Random Fourier Features and Gradient Boostingpaper ] [ video ]
Léo Gautheron, Pascal Germain, Amaury Habrard, Guillaume Metzler, Emilie Morvant, Marc Sebban, Valentina Zantedeschi (ECML 2020)

PAC-Bayesian Contrastive Unsupervised Representation Learningproceedings ] [ supplemental ] [ arXiv ] [ bibtex ] [ video ] [ code ]
Kento Nozawa, Pascal Germain, Benjamin Guedj (UAI 2020)

PAC-Bayes and Domain Adaptationpublished version ] [ arXiv ] [ bibtex ]
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant (Neurocomputing 2020)

Improved PAC-Bayesian Bounds for Linear Regressionproceedings ] [ arXiv ] [ bibtex ]
Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihaly Petreczky (AAAI 2020)

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networksproceedings ] [ arXiv ] [ bibtex ] [ video ] [ code ]
Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette (NeurIPS 2019)

Pseudo-Bayesian Learning with Kernel Fourier Transform as Priorpdf, supplemental ] [ bibtex ] [ poster ] [ code, datasets ]
Gaël Letarte, Emilie Morvant, Pascal Germain (AISTATS 2019)

Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voterspublished version ] [ arXiv preprint ]
Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini (Neurocomputing 2019)

Domain-Adversarial Training of Neural Networkspdf ] [ bib ] [ source code: shallow version | deep version ] [ data ]
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky (JMLR 2016, and Springer 2017*)
*A slighlty shorter version of the JMLR version is published as a book chapter in Domain Adaptation in Computer Vision Applications (Editor: Gabriela Csurka).

PAC-Bayesian Analysis for a two-step Hierarchical Mutliview Learning Approachpdf ]
Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini (ECML 2017)

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

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

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

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

PAC-Bayesian Theory for Transductive Learningpaper, 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 Classifierspaper, supplemental ] [ bib ] [ source code ] [ data ] [ extended version ]
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant (ICML 2013)

A Pseudo-Boolean Set Covering Machinepdf ]
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 Methodspaper ] [ supplemental ]
Pascal Germain, Alexandre Lacoste, Francois Laviolette, Mario Marchand, and Sara Shanian (ICML 2011)

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

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

A PAC-Bayes Risk Bound for General Loss Functionspdf ]
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 Classifierpdf ]
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 domainepdf (french) ] [ slides (french) ]
Pascal Germain (Université Laval, 2015)

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


Selected Talks

27/07/2023 : PAC-Bayesian Learning: A tutorialslides ]
PAC-Bayes Meets Interactive Learning Workshop @ ICML 2023 (Hawaii, US)

06/06/2019 : PAC-Bayesian Learning and Neural Networks; The Binary Activated Caseslides ]
51es Journées de Statistique (Nancy, France)

06/03/2019 : Réseau de neurones artificiels et apprentissage profondslides (french) ]
Journée de l'Enseignement de l'Informatique et de l'Algorithmique (Université de Lille, France)

24/01/2017 : Generalization of the PAC-Bayesian Theory, and Applications to Semi-Supervised Learningslides ]
Modal Seminar (INRIA Lille, France)

20/06/2016 : A New PAC-Bayesian Perspective on Domain Adaptationslides ]
ICML (New-York, US)

02/06/2016 : Variations on the PAC-Bayesian Boundslides ]
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 Adaptationslides ] [ 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 Adaptationslides ]
TAO Seminars (INRIA Saclay / CNRS / Université Paris-Sud, Orsay, France)

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

13/12/2014 : Domain-Adversarial Neural Networksslides ] [ 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 Adaptationslides ]
NIPS 2012 Workshop: Multi-trade-off in Machine Learning (Lake Tahoe, Nevada, US)

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

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

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


Teaching / Enseignement (in French)