Publications

You can also find my articles on my Google Scholar profile.

Articles

Sample Compression for Continual Learning.

Jacob Comeau, Mathieu Bazinet, Pascal Germain, Cem Subakan
ArXiv version to come shortly.

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

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain
Long version of the paper Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning.
ArXiv version of the paper

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

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
Paper accepted at AISTATS 2025. Camera-ready version will be added shortly.
ArXiv version of the paper Code for the paper

Application of machine learning tools to study the synergistic impact of physicochemical properties of peptides and filtration membranes on peptide migration during electrodialysis with filtration membranes

Zain Sanchez-Reinoso, Mathieu Bazinet, Benjamin Leblanc, Jean-Pierre Clément, Pascal Germain, Laurent Bazinet.
Published in the journal Separation and Purification Technology in December 2024.
Link to paper Code for the paper

How peptide migration and fraction bioactivity are modulated by electrical current modes during separation by an electromembrane process: A comprehensive machine learning-based peptidomic approach.

Aurore Cournoyer, Mathieu Bazinet, Jean-Pierre Clément, Pier-Luc Plante, Ismail Fliss, Laurent Bazinet.
Published in the journal Food Research International in November 2024.
Link to paper Code for the paper

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

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain
ArXiv version of the paper

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.

Workshop papers

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

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
Paper accepted at the Workshop on Mathematics of Modern Machine Learning of NeurIPS 2024.
OpenReview forum Link to paper See the poster

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

Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
Paper accepted at the Workshop on Machine Learning and Compression of NeurIPS 2024.
OpenReview forum Link to paper See the poster

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

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain
Paper accepted at the Workshop on Machine Learning and Compression of NeurIPS 2024.
OpenReview forum Link to paper See the poster