# AE-OT-GAN: Training GANs from data specific latent distribution

arXiv: https://arxiv.org/abs/2001.03698 · HTML: https://mlsanity.com/paper/2001.03698/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2020.

## Built on by (most cited first, 13 of 13)

- [Generative Modeling with Optimal Transport Maps](https://mlsanity.com/paper/2110.02999/) (2021)
- [Variational Wasserstein gradient flow](https://mlsanity.com/paper/2112.02424/) (2021)
- [Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport](https://mlsanity.com/paper/2305.14777/) (2023)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [Complexity Matters: Rethinking the Latent Space for Generative Modeling](https://mlsanity.com/paper/2307.08283/) (2023)
- [Analyzing and Improving Optimal-Transport-based Adversarial Networks](https://mlsanity.com/paper/2310.02611/) (2023)
- [A Mathematical Framework for Learning Probability Distributions](https://mlsanity.com/paper/2212.11481/) (2022)
- [A scalable deep learning approach for solving high-dimensional dynamic optimal transport](https://mlsanity.com/paper/2205.07521/) (2022)
- [Spatial and Modal Optimal Transport for Fast Cross-Modal MRI Reconstruction](https://mlsanity.com/paper/2305.02774/) (2023)
- [Solving Prior Distribution Mismatch in Diffusion Models via Optimal Transport](https://mlsanity.com/paper/2410.13431/) (2024)
- [General Autonomous Cybersecurity Defense: Learning Robust Policies for Dynamic Topologies and Diverse Attackers](https://mlsanity.com/paper/2506.22706/) (2025)
- [Efficient Optimal Transport Algorithm by Accelerated Gradient descent](https://mlsanity.com/paper/2104.05802/) (2021)
- [Financial Tail Risk Beyond Lipschitz Continuity via Semi-Discrete Optimal Transport](https://mlsanity.com/paper/2609.27785/) (2026)

## Abstract (arXiv)

Though generative adversarial networks (GANs) areprominent models to generate realistic and crisp images,they often encounter the mode collapse problems and arehard to train, which comes from approximating the intrinsicdiscontinuous distribution transform map with continuousDNNs. The recently proposed AE-OT model addresses thisproblem by explicitly computing the discontinuous distribu-tion transform map through solving a semi-discrete optimaltransport (OT) map in the latent space of the autoencoder.However the generated images are blurry. In this paper, wepropose the AE-OT-GAN model to utilize the advantages ofthe both models: generate high quality images and at thesame time overcome the mode collapse/mixture problems.Specifically, we first faithfully embed the low dimensionalimage manifold into the latent space by training an autoen-coder (AE). Then we compute the optimal transport (OT)map that pushes forward the uniform distribution to the la-tent distribution supported on the latent manifold. Finally,our GAN model is trained to generate high quality imagesfrom the latent distribution, the distribution transform mapfrom which to the empirical data distribution will be con-tinuous. The paired data between the latent code and thereal images gives us further constriction about the generator.Experiments on simple MNIST dataset and complex datasetslike Cifar-10 and CelebA show the efficacy and efficiency ofour proposed method.