Short Bio

After completing my undergraduate studies in actuarial sciences, I reoriented myself: I am currently doing a Ph.D. in computer science at Université Laval, under the supervision of Pascal Germain. I plan to complete my Ph.D. in summer 2026, and am currently looking for a postdoc opportunity to expand my contributions in the fields of PAC-Bayesian (machine learning) theory and interpretability/explainability in machine learning.

Research Interests

      
  • Machine learning theory
  • Generalization bounds
  • Artificial neural networks
                               
  • Interpretability
  • Explainability
  • Ethics

Publications

Peer-Reviewed Works (conferences, journals, workshops)

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks [paper]
Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain (ICML 2025; NeurIPS 2024 – Compression Workshop)
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 [paper]
Zain Sanchez-Reinoso, Mathieu Bazinet, Benjamin Leblanc, Jean-Pierre Clément, Pascal Germain, Laurent Bazinet (Journal of Separation and Purification Technology 2024)
Seeking Interpretability and Explainability in Binary Activated Neural Networks [paper] [preprint]
Benjamin Leblanc, Pascal Germain (xAI 2024)
PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations [paper] [preprint]
Louis Fortier-Dubois, Benjamin Leblanc, Gaël Letarte, François Laviolette, Pascal Germain (CANAI 2023)

Selected Reports

PAC-Bayesian Generalization Guarantees for Fairness on Stochastic and Deterministic Classifiers [ArXiv]
Julien Bastian, Benjamin Leblanc, Pascal Germain, Amaury Habrard, Christine Largeron, Guillaume Metzler, Emilie Morvant, Paul Viallard (2026)
A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes [ArXiv]
Benjamin Leblanc, Pascal Germain (2025)
On the Relationship Between Interpretability and Explainability in Machine Learning [ArXiv]
Benjamin Leblanc, Pascal Germain (2023)

Teaching

Mathématiques pour informaticiens (2023, 2024) - Université Laval, Département d'informatique et de génie logiciel

Affiliations