Pascal Germain

68 papers A* 10A 8Journal 38Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Bound to Disagree: Generalization Bounds via Certifiable Surrogates. CoRR Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
2026	J	`jnl`	PAC-Bayesian Generalization Guarantees for Fairness on Stochastic and Deterministic Classifiers. CoRR Julien Bastian, Benjamin Leblanc, Pascal Germain, Amaury Habrard, Christine Largeron, Guillaume Metzler, Emilie Morvant, Paul Viallard
2025	J	`jnl`	A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes. CoRR Benjamin Leblanc, Pascal Germain
2025	A*	`conf`	Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks. ICML Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain
2025	A	`conf`	Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses. AISTATS Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
2025	J	`jnl`	Sample Compression for Continual Learning. CoRR Jacob Comeau, Mathieu Bazinet, Pascal Germain, Cem Subakan
2024	J	`jnl`	A general framework for the practical disintegration of PAC-Bayesian bounds. Mach. Learn. Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant
2024	A	`conf`	Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice. INTERSPEECH Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan
2024	J	`jnl`	Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice. CoRR Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan
2024	J	`jnl`	Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning. CoRR Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain
2024	J	`jnl`	Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses. CoRR Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
2024	—	`conf`	Seeking Interpretability and Explainability in Binary Activated Neural Networks. xAI (1) Benjamin Leblanc, Pascal Germain
2023	J	`jnl`	Erratum: Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm. J. Mach. Learn. Res. Louis-Philippe Vignault, Audrey Durand, Pascal Germain
2023	J	`jnl`	Interpretability in Machine Learning: on the Interplay with Explainability, Predictive Performances and Models. CoRR Benjamin Leblanc, Pascal Germain
2023	J	`jnl`	Invariant Causal Set Covering Machines. CoRR Thibaud Godon, Baptiste Bauvin, Pascal Germain, Jacques Corbeil, Alexandre Drouin
2023	A*	`conf`	PAC-Bayesian Generalization Bounds for Adversarial Generative Models. ICML Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain
2023	J	`jnl`	PAC-Bayesian Generalization Bounds for Adversarial Generative Models. CoRR Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain
2023	—	`conf`	PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations. Canadian AI Louis Fortier-Dubois, Benjamin Leblanc, Gaël Letarte, François Laviolette, Pascal Germain
2023	A	`conf`	Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data. UAI Baptiste Bauvin, Cécile Capponi, Florence Clerc, Pascal Germain, Sokol Koço, Jacques Corbeil
2023	A*	`conf`	Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory. NeurIPS Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain
2023	J	`jnl`	Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory. CoRR Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain
2022	J	`jnl`	A Greedy Algorithm for Building Compact Binary Activated Neural Networks. CoRR Benjamin Leblanc, Pascal Germain
2022	A*	`conf`	Interpretable Domain Adaptation for Hidden Subdomain Alignment in the Context of Pre-trained Source Models. AAAI Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki
2022	J	`jnl`	Interpretable domain adaptation using unsupervised feature selection on pre-trained source models. Neurocomputing Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki
2021	J	`jnl`	A General Framework for the Derandomization of PAC-Bayesian Bounds. CoRR Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant
2021	J	`jnl`	Learning Aggregations of Binary Activated Neural Networks with Probabilities over Representations. CoRR Louis Fortier-Dubois, Gaël Letarte, Benjamin Leblanc, François Laviolette, Pascal Germain
2021	A*	`conf`	Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound. NeurIPS Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj
2021	J	`jnl`	Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound. CoRR Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj
2021	J	`jnl`	Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound. CoRR Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant
2021	—	`conf`	Self-bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound. ECML/PKDD (2) Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant
2020	J	`jnl`	Implicit Variational Inference: the Parameter and the Predictor Space. CoRR Yann Pequignot, Mathieu Alain, Patrick Dallaire, Alireza Yeganehparast, Pascal Germain, Josée Desharnais, François Laviolette
2020	A*	`conf`	Improved PAC-Bayesian Bounds for Linear Regression. AAAI Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihály Petreczky
2020	—	`conf`	Landmark-Based Ensemble Learning with Random Fourier Features and Gradient Boosting. ECML/PKDD (3) Léo Gautheron, Pascal Germain, Amaury Habrard, Guillaume Metzler, Emilie Morvant, Marc Sebban, Valentina Zantedeschi
2020	J	`jnl`	PAC-Bayes and domain adaptation. Neurocomputing Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2020	A	`conf`	PAC-Bayesian Contrastive Unsupervised Representation Learning. UAI Kento Nozawa, Pascal Germain, Benjamin Guedj
2020	—	`conf`	Target to Source Coordinate-Wise Adaptation of Pre-trained Models. ECML/PKDD (1) Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki
2019	A*	`conf`	Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks. NeurIPS Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette
2019	J	`jnl`	Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks. CoRR Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette
2019	J	`jnl`	Improved PAC-Bayesian Bounds for Linear Regression. CoRR Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihály Petreczky
2019	J	`jnl`	Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting. CoRR Léo Gautheron, Pascal Germain, Amaury Habrard, Emilie Morvant, Marc Sebban, Valentina Zantedeschi
2019	J	`jnl`	Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voters. Neurocomputing Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini
2019	J	`jnl`	PAC-Bayesian Contrastive Unsupervised Representation Learning. CoRR Kento Nozawa, Pascal Germain, Benjamin Guedj
2019	A	`conf`	Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior. AISTATS Gaël Letarte, Emilie Morvant, Pascal Germain
2018	J	`jnl`	Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voters. CoRR Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini
2018	J	`jnl`	Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior. CoRR Gaël Letarte, Emilie Morvant, Pascal Germain
2017	—	`ch.`	Domain-Adversarial Training of Neural Networks. Domain Adaptation in Computer Vision Applications Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor S. Lempitsky
2017	—	`conf`	PAC-Bayesian Analysis for a Two-Step Hierarchical Multiview Learning Approach. ECML/PKDD (2) Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini
2016	A*	`conf`	A New PAC-Bayesian Perspective on Domain Adaptation. ICML Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2016	J	`jnl`	Domain-Adversarial Training of Neural Networks. J. Mach. Learn. Res. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor S. Lempitsky
2016	A	`conf`	PAC-Bayesian Bounds based on the Rényi Divergence. AISTATS Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy
2016	—	`conf`	PAC-Bayesian Theory Meets Bayesian Inference. NIPS Pascal Germain, Francis R. Bach, Alexandre Lacoste, Simon Lacoste-Julien
2016	J	`jnl`	PAC-Bayesian Theory Meets Bayesian Inference. CoRR Pascal Germain, Francis R. Bach, Alexandre Lacoste, Simon Lacoste-Julien
2015	J	`jnl`	A New PAC-Bayesian Perspective on Domain Adaptation. CoRR Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2015	J	`jnl`	An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context. CoRR Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2015	J	`jnl`	Domain-Adversarial Training of Neural Networks. CoRR Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor S. Lempitsky
2015	J	`jnl`	PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers. CoRR Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2015	J	`jnl`	Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm. CoRR Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, Jean-Francis Roy
2015	J	`jnl`	Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm. J. Mach. Learn. Res. Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, Jean-Francis Roy
2014	J	`jnl`	Domain-Adversarial Neural Networks. CoRR Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand
2014	A	`conf`	PAC-Bayesian Theory for Transductive Learning. AISTATS Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy
2013	—	`conf`	A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers. ICML (3) Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2012	A	`conf`	A Pseudo-Boolean Set Covering Machine. CP Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, Claude-Guy Quimper
2012	J	`jnl`	PAC-Bayesian Learning and Domain Adaptation CoRR Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
2011	A*	`conf`	A PAC-Bayes Sample-compression Approach to Kernel Methods. ICML Pascal Germain, Alexandre Lacoste, François Laviolette, Mario Marchand, Sara Shanian
2009	—	`conf`	From PAC-Bayes Bounds to KL Regularization. NIPS Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, Sara Shanian
2009	A*	`conf`	PAC-Bayesian learning of linear classifiers. ICML Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand
2006	—	`conf`	A PAC-Bayes Risk Bound for General Loss Functions. NIPS Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand
2006	—	`conf`	PAC-Bayes Bounds for the Risk of the Majority Vote and the Variance of the Gibbs Classifier. NIPS Alexandre Lacasse, François Laviolette, Mario Marchand, Pascal Germain, Nicolas Usunier