A Note on the Efficient Evaluation of PAC-Bayes Bounds. (arXiv:2209.05188v2 [cs.LG] UPDATED)

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.

arxiv bayes evaluation