Conference item
Conditionally Gaussian PAC-Bayes
- 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 sur...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Version of record, pdf, 1.4MB)
-
- Publication website:
- https://proceedings.mlr.press/v151/clerico22a.html
Authors
Funding
+ Engineering and Physical Sciences Research Council
More from this funder
Grant:
56726
EP/R013616/1
Bibliographic Details
- Publisher:
- Journal of Machine Learning Research Publisher's website
- Series:
- Proceedings of Machine Learning Research
- Series number:
- 151
- Pages:
- 2311-2329
- Publication date:
- 2022-05-03
- Acceptance date:
- 2022-01-18
- Event title:
- 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022)
- Event location:
- Virtual event
- Event website:
- https://aistats.org/aistats2022/
- Event start date:
- 2022-03-28
- Event end date:
- 2022-03-30
- ISSN:
-
2640-3498
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1243098
- Local pid:
- pubs:1243098
- Deposit date:
- 2022-12-08
Terms of use
- Copyright holder:
- Clerico et al.
- Copyright date:
- 2022
- Rights statement:
- Copyright 2021 by the author(s).
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record