Pascal Germain

According to our database, Pascal Germain authored at least 47 papers between 2006 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

A general framework for the practical disintegration of PAC-Bayesian bounds.

Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant

Mach. Learn., February, 2024

Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning.

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain

CoRR, 2024

Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice.

Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan

CoRR, 2024

Seeking Interpretability and Explainability in Binary Activated Neural Networks.

Benjamin Leblanc, Pascal Germain

Proceedings of the Explainable Artificial Intelligence, 2024

2023

Erratum: Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm.

Louis-Philippe Vignault, Audrey Durand, Pascal Germain

J. Mach. Learn. Res., 2023

Interpretability in Machine Learning: on the Interplay with Explainability, Predictive Performances and Models.

Benjamin Leblanc, Pascal Germain

CoRR, 2023

Invariant Causal Set Covering Machines.

Thibaud Godon, Baptiste Bauvin, Pascal Germain, Jacques Corbeil, Alexandre Drouin

CoRR, 2023

Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data.

Baptiste Bauvin, Cécile Capponi, Florence Clerc, Pascal Germain, Sokol Koço, Jacques Corbeil

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory.

Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

PAC-Bayesian Generalization Bounds for Adversarial Generative Models.

Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

Proceedings of the International Conference on Machine Learning, 2023

PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations.

Louis Fortier-Dubois, Benjamin Leblanc, Gaël Letarte, François Laviolette, Pascal Germain

Proceedings of the 36th Canadian Conference on Artificial Intelligence, 2023

2022

Interpretable domain adaptation using unsupervised feature selection on pre-trained source models.

Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki

Neurocomputing, 2022

A Greedy Algorithm for Building Compact Binary Activated Neural Networks.

Benjamin Leblanc, Pascal Germain

CoRR, 2022

Interpretable Domain Adaptation for Hidden Subdomain Alignment in the Context of Pre-trained Source Models.

Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Learning Aggregations of Binary Activated Neural Networks with Probabilities over Representations.

Louis Fortier-Dubois, Gaël Letarte, Benjamin Leblanc, François Laviolette, Pascal Germain

CoRR, 2021

A General Framework for the Derandomization of PAC-Bayesian Bounds.

Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant

CoRR, 2021

Self-bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound.

Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2021

Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound.

Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

PAC-Bayes and domain adaptation.

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Neurocomputing, 2020

Implicit Variational Inference: the Parameter and the Predictor Space.

Yann Pequignot, Mathieu Alain, Patrick Dallaire, Alireza Yeganehparast, Pascal Germain, Josée Desharnais, François Laviolette

CoRR, 2020

PAC-Bayesian Contrastive Unsupervised Representation Learning.

Kento Nozawa, Pascal Germain, Benjamin Guedj

Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence, 2020

Target to Source Coordinate-Wise Adaptation of Pre-trained Models.

Luxin Zhang, Pascal Germain, Yacine Kessaci, Christophe Biernacki

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

Landmark-Based Ensemble Learning with Random Fourier Features and Gradient Boosting.

Léo Gautheron, Pascal Germain, Amaury Habrard, Guillaume Metzler, Emilie Morvant, Marc Sebban, Valentina Zantedeschi

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

Improved PAC-Bayesian Bounds for Linear Regression.

Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihály Petreczky

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voters.

Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini

Neurocomputing, 2019

Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting.

Léo Gautheron, Pascal Germain, Amaury Habrard, Emilie Morvant, Marc Sebban, Valentina Zantedeschi

CoRR, 2019

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks.

Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior.

Gaël Letarte, Emilie Morvant, Pascal Germain

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2017

Domain-Adversarial Training of Neural Networks.

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor S. Lempitsky

Proceedings of the Domain Adaptation in Computer Vision Applications., 2017

PAC-Bayesian Analysis for a Two-Step Hierarchical Multiview Learning Approach.

Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2017

2016

Domain-Adversarial Training of Neural Networks.

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor S. Lempitsky

J. Mach. Learn. Res., 2016

PAC-Bayesian Theory Meets Bayesian Inference.

Pascal Germain, Francis R. Bach, Alexandre Lacoste, Simon Lacoste-Julien

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

A New PAC-Bayesian Perspective on Domain Adaptation.

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Proceedings of the 33nd International Conference on Machine Learning, 2016

PAC-Bayesian Bounds based on the Rényi Divergence.

Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015

Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm.

Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, Jean-Francis Roy

J. Mach. Learn. Res., 2015

PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers.

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

CoRR, 2015

An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context.

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

CoRR, 2015

2014

Domain-Adversarial Neural Networks.

Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand

CoRR, 2014

PAC-Bayesian Theory for Transductive Learning.

Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy

Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, 2014

2013

A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers.

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Proceedings of the 30th International Conference on Machine Learning, 2013

2012

PAC-Bayesian Learning and Domain Adaptation

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

CoRR, 2012

A Pseudo-Boolean Set Covering Machine.

Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, Claude-Guy Quimper

Proceedings of the Principles and Practice of Constraint Programming, 2012

2011

A PAC-Bayes Sample-compression Approach to Kernel Methods.

Pascal Germain, Alexandre Lacoste, François Laviolette, Mario Marchand, Sara Shanian

Proceedings of the 28th International Conference on Machine Learning, 2011

2009

From PAC-Bayes Bounds to KL Regularization.

Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, Sara Shanian

Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

PAC-Bayesian learning of linear classifiers.

Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand

Proceedings of the 26th Annual International Conference on Machine Learning, 2009

2006

PAC-Bayes Bounds for the Risk of the Majority Vote and the Variance of the Gibbs Classifier.

Alexandre Lacasse, François Laviolette, Mario Marchand, Pascal Germain, Nicolas Usunier

Proceedings of the Advances in Neural Information Processing Systems 19, 2006

A PAC-Bayes Risk Bound for General Loss Functions.

Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand

Proceedings of the Advances in Neural Information Processing Systems 19, 2006