Generalization bounds: Perspectives from information theory and PAC-Bayes

F Hellström, G Durisi, B Guedj… - … and Trends® in …, 2025 - nowpublishers.com
A fundamental question in theoretical machine learning is generalization. Over the past
decades, the PAC-Bayesian approach has been established as a flexible framework to …

Sample compression unleashed: New generalization bounds for real valued losses

M Bazinet, V Zantedeschi, P Germain - arxiv preprint arxiv:2409.17932, 2024 - arxiv.org
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, generally …

Lifted Coefficient of Determination: Fast model-free prediction intervals and likelihood-free model comparison

D Salnikov, K Michalewicz, D Leonte - arxiv preprint arxiv:2410.08958, 2024 - arxiv.org
We propose the $\textit {lifted linear model} $, and derive model-free prediction intervals that
become tighter as the correlation between predictions and observations increases. These …