activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

Benjamin Leblanc, Louis-Jacob Lebel, Teddy Kana +1

Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet, despite the breadth of exi…

cs.LG2025

A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes

Benjamin Leblanc, Pascal Germain

PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formul…

cs.LG2025

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

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours +2

Both PAC-Bayesian and Sample Compress learning frameworks are instrumental for deriving tight (non-vacuous) generalization bounds for neural networks. We leverage these results in…

cs.LG2024

Seeking Interpretability and Explainability in Binary Activated Neural Networks

Benjamin Leblanc, Pascal Germain

We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide g…

cs.LG2024

On the Relationship Between Interpretability and Explainability in Machine Learning

Benjamin Leblanc, Pascal Germain

Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshoot…