Pascal Germain
About
Appointed Canada CIFAR AI Chair – 2019
Pascal Germain is a Canada CIFAR AI Chair at Mila, and an assistant professor in the department of computer and software engineering at Université Laval.
Germain’s main research interests are statistical learning theory, including PAC-Bayesian theory, and learning algorithms.
Relevant Publications
Viallard, P., Germain, P., Habrard, A., & Morvant, E. (2023). A general framework for the practical disintegration of PAC-Bayesian bounds. Machine Learning, 1-86.
Diarra Mbacke, S., Clerc, F., & Germain, P. (2023). Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory. NeurIPS
Diarra Mbacke, S., Clerc, F., & Germain, P. (2023). PAC-Bayesian Generalization Bounds for Adversarial Generative Models. ICML.
Fortier-Dubois, L., Leblanc, B., Letarte, G., Laviolette, F., Germain P. (2023). PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations. CANAI
Zantedeschi, V., Viallard, P., Morvant, E., Emonet, R., Habrard, A., Germain, P., & Guedj, B. (2021). Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound.