# Variational Autoencoders with Normalizing Flow Decoders

arXiv: https://arxiv.org/abs/2004.05617 · HTML: https://mlsanity.com/paper/2004.05617/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Preventing Oversmoothing in VAE via Generalized Variance Parameterization](https://mlsanity.com/paper/2102.08663/) (2021)
- [InVAErt networks: a data-driven framework for model synthesis and identifiability analysis](https://mlsanity.com/paper/2307.12586/) (2023)
- [Deterministic training of generative autoencoders using invertible layers](https://mlsanity.com/paper/2205.09546/) (2022)
- [Sequential Representation Learning via Static-Dynamic Conditional Disentanglement](https://mlsanity.com/paper/2408.05599/) (2024)
- [Data Augmentation for Multivariate Time Series Classification: An Experimental Study](https://mlsanity.com/paper/2406.06518/) (2024)
- [Enhancing variational generation through self-decomposition](https://mlsanity.com/paper/2202.02738/) (2022)
- [Multisymplectic Formulation of Deep Learning Using Mean--Field Type Control and Nonlinear Stability of Training Algorithm](https://mlsanity.com/paper/2207.12242/) (2022)

## Abstract (arXiv)

Recently proposed normalizing flow models such as Glow have been shown to be able to generate high quality, high dimensional images with relatively fast sampling speed. Due to their inherently restrictive architecture, however, it is necessary that they are excessively deep in order to train effectively. In this paper we propose to combine Glow with an underlying variational autoencoder in order to counteract this issue. We demonstrate that our proposed model is competitive with Glow in terms of image quality and test likelihood while requiring far less time for training.