On PAC-Bayesian reconstruction guarantees for VAEs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

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.
Fichier principal
Vignette du fichier
2202.11455.pdf (2.18 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03587178 , version 1 (24-02-2022)

Identifiers

Cite

Badr-Eddine Chérief-Abdellatif, Yuyang Shi, Arnaud Doucet, Benjamin Guedj. On PAC-Bayesian reconstruction guarantees for VAEs. 25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022, Mar 2022, Valencia / Virtual, Spain. ⟨hal-03587178⟩
57 View
187 Download

Altmetric

Share

Gmail Facebook X LinkedIn More