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.
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.
Viallard, P., Germain, P., Habrard, A., & Morvant, E. (2021). Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound.
Viallard, P., Germain, P., Habrard, A., & Morvant, E. (2021). A General Framework for the Derandomization of PAC-Bayesian Bounds.
Pequignot, Y., Alain, M., Dallaire, P., Yeganehparast, A., Germain, P., Desharnais, J., & Laviolette, F. (2020). Implicit Variational Inference: the Parameter and the Predictor Space.
Zhang, L., Germain, P., Kessaci, Y., & Biernacki, C. (2020). Target to Source Coordinate-wise Adaptation of Pre-trained Models. In ECML PKDD 2020-The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases.
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.