# Fisher GAN

arXiv: https://arxiv.org/abs/1705.09675 · HTML: https://mlsanity.com/paper/1705.09675/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2017.

## Built on by (most cited first, 22 of 22)

- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Generative Multiplane Images: Making a 2D GAN 3D-Aware](https://mlsanity.com/paper/2207.10642/) (2022)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [Realizing GANs via a Tunable Loss Function](https://mlsanity.com/paper/2106.05232/) (2021)
- [DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data](https://mlsanity.com/paper/2211.14694/) (2022)
- [Training Generative Adversarial Networks in One Stage](https://mlsanity.com/paper/2103.00430/) (2021)
- [Addressing GAN Training Instabilities via Tunable Classification Losses](https://mlsanity.com/paper/2310.18291/) (2023)
- [Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems](https://mlsanity.com/paper/2103.08086/) (2021)
- [Robust Vector Quantized-Variational Autoencoder](https://mlsanity.com/paper/2202.01987/) (2022)
- [AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss](https://mlsanity.com/paper/2608.11205/) (2026)
- [Bi-Discriminator Class-Conditional Tabular GAN](https://mlsanity.com/paper/2111.06549/) (2021)
- [Hoeffding's Inequality for Markov Chains under Generalized Concentrability Condition](https://mlsanity.com/paper/2310.02941/) (2023)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [Learning with Stochastic Orders](https://mlsanity.com/paper/2205.13684/) (2022)
- [CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization](https://mlsanity.com/paper/2404.00521/) (2024)
- [CF-GO-Net: A Universal Distribution Learner via Characteristic Function Networks with Graph Optimizers](https://mlsanity.com/paper/2409.12610/) (2024)
- [Scalable Sobolev IPM for Probability Measures on a Graph](https://mlsanity.com/paper/2502.00737/) (2025)
- [RCC-GAN: Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis](https://mlsanity.com/paper/2205.11693/) (2022)
- [RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks](https://mlsanity.com/paper/2207.06858/) (2022)
- [A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision](https://mlsanity.com/paper/2311.00995/) (2023)
- [Kolmogorov-Smirnov GAN](https://mlsanity.com/paper/2406.19948/) (2024)
- [The informativeness of the gradient revisited](https://mlsanity.com/paper/2505.22158/) (2025)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs. Fisher GAN defines a critic with a data dependent constraint on its second order moments. We show in this paper that Fisher GAN allows for stable and time efficient training that does not compromise the capacity of the critic, and does not need data independent constraints such as weight clipping. We analyze our Fisher IPM theoretically and provide an algorithm based on Augmented Lagrangian for Fisher GAN. We validate our claims on both image sample generation and semi-supervised classification using Fisher GAN.