A Note on the Efficient Evaluation of PAC-Bayes Bounds
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 5 of its 8 references that are in the map. First posted on arXiv 12 Sep 2022.
Builds on
5 of 8 references.
References · 5
- 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
- 2022Non-Vacuous Generalisation Bounds for Shallow Neural Networkscited by 22
- 2021Progress in Self-Certified Neural Networkscited by 10
- 2021Conditionally Gaussian PAC-Bayescited by 7
- 2022A Note on the Chernoff Bound for Random Variables in the Unit Intervalcited by 7
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 1.
2 papers.