Conference item icon

Conference item

On PAC-Bayesian reconstruction guarantees for VAEs

Abstract:
Despite its wide use and empirical successes, the theoretical understanding and study of the behaviour and performance of the variational autoencoder (VAE) have only emerged in the past few years. We contribute to this recent line of work by analysing the VAE’s reconstruction ability for unseen test data, leveraging arguments from the PAC-Bayes theory. We provide generalisation bounds on the theoretical reconstruction error, and provide insights on the regularisation effect of VAE objectives. We illustrate our theoretical results with supporting experiments on classical benchmark datasets.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Publication website:
https://proceedings.mlr.press/v151/cherief-abdellatif22a.html

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Statistics
Oxford college:
Hertford College
Role:
Author
ORCID:
0000-0002-7662-419X


Publisher:
Journal of Machine Learning Research
Host title:
Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022)
Volume:
151
Pages:
3066-3079
Series:
Proceedings of Machine Learning Research
Publication date:
2022-09-18
Event title:
25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022)
Event location:
Valencia, Spain
Event website:
http://aistats.org/aistats2022/
Event start date:
2022-03-28
Event end date:
2022-03-30
ISSN:
2640-3498


Language:
English
Keywords:
Pubs id:
1276300
Local pid:
pubs:1276300
Deposit date:
2022-12-08

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP