On PAC-Bayesian reconstruction guarantees for VAEs

Badr-Eddine Chérief-Abdellatif, Yuyang Shi, Arnaud Doucet, Benjamin Guedj
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:3066-3079, 2022.

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 this Paper

BibTeX
@InProceedings{pmlr-v151-cherief-abdellatif22a, title = { On PAC-Bayesian reconstruction guarantees for VAEs }, author = {Ch\'erief-Abdellatif, Badr-Eddine and Shi, Yuyang and Doucet, Arnaud and Guedj, Benjamin}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {3066--3079}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/cherief-abdellatif22a/cherief-abdellatif22a.pdf}, url = {https://proceedings.mlr.press/v151/cherief-abdellatif22a.html}, 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. } }
Endnote
%0 Conference Paper %T On PAC-Bayesian reconstruction guarantees for VAEs %A Badr-Eddine Chérief-Abdellatif %A Yuyang Shi %A Arnaud Doucet %A Benjamin Guedj %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-cherief-abdellatif22a %I PMLR %P 3066--3079 %U https://proceedings.mlr.press/v151/cherief-abdellatif22a.html %V 151 %X 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.
APA
Chérief-Abdellatif, B., Shi, Y., Doucet, A. & Guedj, B.. (2022). On PAC-Bayesian reconstruction guarantees for VAEs . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:3066-3079 Available from https://proceedings.mlr.press/v151/cherief-abdellatif22a.html.

Related Material