Pascal Germain

Publications

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks. Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain. At International Conference on Machine Learning (ICML), 2025.

Sample compression unleashed: New generalization bounds for real valued losses. Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain. At International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.

Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning. Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Pascal Germain, Alexandre Drouin. At Workshop at the Neural Information Processing Systems (NeurIPS), 2024.

Sample compression unleashed: New generalization bounds for real valued losses. Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain. At Workshop at the Neural Information Processing Systems (NeurIPS), 2024.

Invariant Causal Set Covering Machines. Thibaud Godon, Baptiste Bauvin, Pascal Germain, Jacques Corbeil, Alexandre Drouin. At Workshop on Spurious Correlations, Invariance, and Stability (ICML), 2023.