Back to Search
Start Over
Conditionally Gaussian PAC-Bayes
- Source :
- Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:2311-2329, 2022
- Publication Year :
- 2021
-
Abstract
- Recent studies have empirically investigated different methods to train stochastic neural networks on a classification task by optimising a PAC-Bayesian bound via stochastic gradient descent. Most of these procedures need to replace the misclassification error with a surrogate loss, leading to a mismatch between the optimisation objective and the actual generalisation bound. The present paper proposes a novel training algorithm that optimises the PAC-Bayesian bound, without relying on any surrogate loss. Empirical results show that this approach outperforms currently available PAC-Bayesian training methods.
- Subjects :
- Computer Science - Machine Learning
Statistics - Machine Learning
Subjects
Details
- Database :
- arXiv
- Journal :
- Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:2311-2329, 2022
- Publication Type :
- Report
- Accession number :
- edsarx.2110.11886
- Document Type :
- Working Paper