Posterior Collapse of a Linear Latent Variable Model

Zihao Wang; Liu Ziyin

NeurIPS 2022accept30 citations

Posterior Collapse of a Linear Latent Variable Model

Abstract

This work identifies the existence and cause of a type of posterior collapse that frequently occurs in the Bayesian deep learning practice. For a general linear latent variable model that includes linear variational autoencoders as a special case, we precisely identify the nature of posterior collapse to be the competition between the likelihood and the regularization of the mean due to the prior. Our result also suggests that posterior collapse may be a general problem of learning for deeper architectures and deepens our understanding of Bayesian deep learning.

Bayesian deep learningloss landscapeposterior collapselinear modelVAE

BibTeX

@inproceedings{
wang2022posterior,
title={Posterior Collapse of a Linear Latent Variable Model},
author={Zihao Wang and Liu Ziyin},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=zAc2a6_0aHb}
}