When utilising PAC-Bayes theory for risk certification, it is usually necessary to estimate and bound the Gibbs risk of the PAC-Bayes posterior. Many works in the literature employ a method for this which requires a large number of passes of the dataset, incurring high computational cost. This manuscript presents a very general alternative which makes computational savings on the order of the dataset size.
@article{arxiv.2209.05188,
title = {A Note on the Efficient Evaluation of PAC-Bayes Bounds},
author = {Felix Biggs},
journal= {arXiv preprint arXiv:2209.05188},
year = {2022}
}