4 papers
Bound to Disagree: Generalization Bounds via Certifiable Surrogates
Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
Generalization bounds for deep learning models are typically vacuous, not computable or restricted to specific model classes. In this paper, we tackle these issues by providing new…
Sample Compression for Self Certified Continual Learning
Jacob Comeau, Mathieu Bazinet, Pascal Germain +1
Continual learning algorithms aim to learn from a sequence of tasks. In order to avoid catastrophic forgetting, most existing approaches rely on heuristics and do not provide compu…
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…
Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses
Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, gener…