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

ICML 2025

Long version of Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

AISTATS 2025

Application of machine learning tools to study the synergistic impact of physicochemical properties.

Zain Sanchez-Reinoso, Mathieu Bazinet, Benjamin Leblanc, Jean-Pierre Clément, Pascal Germain, Laurent Bazinet

Separation and Purification Technology, Dec 2024

How peptide migration and fraction bioactivity are modulated by electrical current modes...

Aurore Cournoyer, Mathieu Bazinet, Jean-Pierre Clément, Pier-Luc Plante, Ismail Fliss, Laurent Bazinet

Food Research International, Nov 2024

Sample Compression for Self-Certified Continual Learning

Jacob Comeau*, Mathieu Bazinet*, Pascal Germain, Cem Subakan

* indicates equal contributions.

Wavelet-Based Feature Map for Kernel Approximation.

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

This article was submitted at a conference in 2023, but was never published.

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

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

Workshop on Mathematics of Modern Machine Learning of NeurIPS 2024

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

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

Workshop on Machine Learning and Compression of NeurIPS 2024

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

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

Workshop on Machine Learning and Compression of NeurIPS 2024