| 2025 | AISTATS | Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses. | Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain |
| 2025 | ICML | Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks. | Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain |
| 2024 | Interspeech | Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice. | Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan |
| 2023 | AI | PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations. | Louis Fortier-Dubois, Benjamin Leblanc, Gal Letarte, Franois Laviolette, Pascal Germain |
| 2023 | ICML | PAC-Bayesian Generalization Bounds for Adversarial Generative Models. | Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain |
| 2023 | UAI | Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data. | Baptiste Bauvin, Ccile Capponi, Florence Clerc, Pascal Germain, Sokol Koo, Jacques Corbeil |
| 2022 | AAAI | Interpretable Domain Adaptation for Hidden Subdomain Alignment in the Context of Pre-trained Source Models. | Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki |
| 2020 | AAAI | Improved PAC-Bayesian Bounds for Linear Regression. | Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihly Petreczky |
| 2020 | UAI | PAC-Bayesian Contrastive Unsupervised Representation Learning. | Kento Nozawa, Pascal Germain, Benjamin Guedj |
| 2019 | AISTATS | Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior. | Gal Letarte, Emilie Morvant, Pascal Germain |
| 2016 | AISTATS | PAC-Bayesian Bounds based on the Rnyi Divergence. | Luc Bgin, Pascal Germain, Franois Laviolette, Jean-Francis Roy |
| 2016 | ICML | A New PAC-Bayesian Perspective on Domain Adaptation. | Pascal Germain, Amaury Habrard, Franois Laviolette, Emilie Morvant |
| 2014 | AISTATS | PAC-Bayesian Theory for Transductive Learning. | Luc Bgin, Pascal Germain, Franois Laviolette, Jean-Francis Roy |
| 2013 | ICML | A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers. | Pascal Germain, Amaury Habrard, Franois Laviolette, Emilie Morvant |
| 2012 | CP | A Pseudo-Boolean Set Covering Machine. | Pascal Germain, Sbastien Gigure, Jean-Francis Roy, Brice Zirakiza, Franois Laviolette, Claude-Guy Quimper |
| 2011 | ICML | A PAC-Bayes Sample-compression Approach to Kernel Methods. | Pascal Germain, Alexandre Lacoste, Franois Laviolette, Mario Marchand, Sara Shanian |
| 2009 | ICML | PAC-Bayesian learning of linear classifiers. | Pascal Germain, Alexandre Lacasse, Franois Laviolette, Mario Marchand |