Mathieu Bazinet

According to our database, Mathieu Bazinet authored at least 5 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Bound to Disagree: Generalization Bounds via Certifiable Surrogates.

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

CoRR, February, 2026

2025

Sample Compression for Continual Learning.

Jacob Comeau, Mathieu Bazinet, Pascal Germain, Cem Subakan

CoRR, March, 2025

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks.

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

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses.

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

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

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

CoRR, 2024