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.
Cite
Text
Chérief-Abdellatif et al. "On PAC-Bayesian Reconstruction Guarantees for VAEs." Artificial Intelligence and Statistics, 2022.Markdown
[Chérief-Abdellatif et al. "On PAC-Bayesian Reconstruction Guarantees for VAEs." Artificial Intelligence and Statistics, 2022.](https://mlanthology.org/aistats/2022/cheriefabdellatif2022aistats-pacbayesian/)BibTeX
@inproceedings{cheriefabdellatif2022aistats-pacbayesian,
title = {{On PAC-Bayesian Reconstruction Guarantees for VAEs}},
author = {Chérief-Abdellatif, Badr-Eddine and Shi, Yuyang and Doucet, Arnaud and Guedj, Benjamin},
booktitle = {Artificial Intelligence and Statistics},
year = {2022},
pages = {3066-3079},
volume = {151},
url = {https://mlanthology.org/aistats/2022/cheriefabdellatif2022aistats-pacbayesian/}
}