Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

07/14/2020 ∙ by Yaniv Yacoby, et al. ∙ 0

Variational Auto-encoders (VAEs) are deep generative latent variable models that are widely used for a number of downstream tasks. While it has been demonstrated that VAE training can suffer from a number of pathologies, existing literature lacks characterizations of exactly when these pathologies occur and how they impact down-stream task performance. In this paper we concretely characterize conditions under which VAE training exhibits pathologies and connect these failure modes to undesirable effects on specific downstream tasks - learning compressed and disentangled representations, adversarial robustness and semi-supervised learning.



There are no comments yet.


page 5

page 24

page 26

page 27

page 28

page 29

page 30

page 31

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.