English

A Note on the Efficient Evaluation of PAC-Bayes Bounds

Machine Learning 2022-10-21 v2 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}

Comments

4 pages

R2 v1 2026-06-28T01:07:23.089Z