Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

07/14/2020

∙

by   Yaniv Yacoby, et al.

∙

0

∙

share

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.