# A Probe Towards Understanding GAN and VAE Models

arXiv: https://arxiv.org/abs/1812.05676 · HTML: https://mlsanity.com/paper/1812.05676/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2018.

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

- [Query2CAD: Generating CAD models using natural language queries](https://mlsanity.com/paper/2406.00144/) (2024)
- [A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources](https://mlsanity.com/paper/2203.07018/) (2022)
- [Bi-Discriminator Class-Conditional Tabular GAN](https://mlsanity.com/paper/2111.06549/) (2021)
- [Robustness Analysis of Deep Learning Models for Population Synthesis](https://mlsanity.com/paper/2211.13339/) (2022)
- [Generative Model-Driven Synthetic Training Image Generation: An Approach to Cognition in Rail Defect Detection](https://mlsanity.com/paper/2401.00393/) (2023)
- [Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm](https://mlsanity.com/paper/2502.10650/) (2025)
- [Exploring the Effectiveness of Dataset Synthesis: An application of Apple Detection in Orchards](https://mlsanity.com/paper/2306.11763/) (2023)

## Abstract (arXiv)

This project report compares some known GAN and VAE models proposed prior to 2017. There has been significant progress after we finished this report. We upload this report as an introduction to generative models and provide some personal interpretations supported by empirical evidence. Both generative adversarial network models and variational autoencoders have been widely used to approximate probability distributions of data sets. Although they both use parametrized distributions to approximate the underlying data distribution, whose exact inference is intractable, their behaviors are very different. We summarize our experiment results that compare these two categories of models in terms of fidelity and mode collapse. We provide a hypothesis to explain their different behaviors and propose a new model based on this hypothesis. We further tested our proposed model on MNIST dataset and CelebA dataset.