# Towards Principled Methods for Training Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1701.04862 · HTML: https://mlsanity.com/paper/1701.04862/

## Key facts

- Cited by 464 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2017.

## Built on by (most cited first, 30 of 464)

- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation](https://mlsanity.com/paper/2301.03396/) (2023)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion](https://mlsanity.com/paper/2209.03855/) (2022)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [An Introduction to Deep Generative Modeling](https://mlsanity.com/paper/2103.05180/) (2021)
- [Generative Modeling with Optimal Transport Maps](https://mlsanity.com/paper/2110.02999/) (2021)
- [NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models](https://mlsanity.com/paper/2304.09787/) (2023)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [Fighting Copycat Agents in Behavioral Cloning from Observation Histories](https://mlsanity.com/paper/2010.14876/) (2020)
- [Towards Implicit Text-Guided 3D Shape Generation](https://mlsanity.com/paper/2203.14622/) (2022)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [Risk-Averse Offline Reinforcement Learning](https://mlsanity.com/paper/2102.05371/) (2021)
- [GANs for Medical Image Synthesis: An Empirical Study](https://mlsanity.com/paper/2105.05318/) (2021)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [High-resolution Face Swapping via Latent Semantics Disentanglement](https://mlsanity.com/paper/2203.15958/) (2022)

## Abstract (arXiv)

The goal of this paper is not to introduce a single algorithm or method, but to make theoretical steps towards fully understanding the training dynamics of generative adversarial networks. In order to substantiate our theoretical analysis, we perform targeted experiments to verify our assumptions, illustrate our claims, and quantify the phenomena. This paper is divided into three sections. The first section introduces the problem at hand. The second section is dedicated to studying and proving rigorously the problems including instability and saturation that arize when training generative adversarial networks. The third section examines a practical and theoretically grounded direction towards solving these problems, while introducing new tools to study them.