# On the Implicit Assumptions of GANs

arXiv: https://arxiv.org/abs/1811.12402 · HTML: https://mlsanity.com/paper/1811.12402/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

## Built on by (most cited first, 6 of 6)

- [NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models](https://mlsanity.com/paper/2304.09787/) (2023)
- [Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis](https://mlsanity.com/paper/2307.10094/) (2023)
- [Towards A Multi-agent System for Online Hate Speech Detection](https://mlsanity.com/paper/2105.01129/) (2021)
- [Exploiting the Hidden Tasks of GANs: Making Implicit Subproblems Explicit](https://mlsanity.com/paper/2101.11863/) (2021)
- [Overcoming challenges in leveraging GANs for few-shot data augmentation](https://mlsanity.com/paper/2203.16662/) (2022)
- [Survival Analysis with Adversarial Regularization](https://mlsanity.com/paper/2312.16019/) (2023)

## Abstract (arXiv)

Generative adversarial nets (GANs) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees. A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are commonly made, but the message seems to have been lost amid the optimism of recent years. We believe the identified problems deserve more attention, and highlight the implications on both the properties of GANs and the trajectory of research on probabilistic models. We recently proposed an alternative method that sidesteps these problems.