Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Keywords: Variational Autoencoders, Variational Inference, VAE, Approximate Inference, Semi-Supervision

Abstract: 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, such as learning compressed and disentangled representations, adversarial robustness and semi-supervised learning.

One-sentence Summary: We concretely characterize conditions under which VAE training exhibits pathologies and connect these failure modes to undesirable effects on specific downstream tasks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=1naT12Saf0