# ExGAN: Adversarial Generation of Extreme Samples

arXiv: https://arxiv.org/abs/2009.08454 · HTML: https://mlsanity.com/paper/2009.08454/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 29 of 29)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network](https://mlsanity.com/paper/2309.00638/) (2023)
- [A VAE Approach to Sample Multivariate Extremes](https://mlsanity.com/paper/2306.10987/) (2023)
- [Sketch-Based Anomaly Detection in Streaming Graphs](https://mlsanity.com/paper/2106.04486/) (2021)
- [Inference and Sampling for Archimax Copulas](https://mlsanity.com/paper/2205.14025/) (2022)
- [Beyond the Norm: A Survey of Synthetic Data Generation for Rare Events](https://mlsanity.com/paper/2506.06380/) (2025)
- [Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators](https://mlsanity.com/paper/2101.04645/) (2021)
- [Extreme heatwave sampling and prediction with analog Markov chain and comparisons with deep learning](https://mlsanity.com/paper/2307.09060/) (2023)
- [Generative Machine Learning for Multivariate Angular Simulation](https://mlsanity.com/paper/2504.21505/) (2025)
- [GraphAnoGAN: Detecting Anomalous Snapshots from Attributed Graphs](https://mlsanity.com/paper/2106.15504/) (2021)
- [Controlling Weather Field Synthesis Using Variational Autoencoders](https://mlsanity.com/paper/2108.00048/) (2021)
- [OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary](https://mlsanity.com/paper/2110.15273/) (2021)
- [Combining deep generative models with extreme value theory for synthetic hazard simulation: a multivariate and spatially coherent approach](https://mlsanity.com/paper/2311.18521/) (2023)
- [Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss](https://mlsanity.com/paper/2410.22381/) (2024)
- [E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation](https://mlsanity.com/paper/2606.01634/) (2026)
- [TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures](https://mlsanity.com/paper/2306.17248/) (2023)
- [Simulation of Multivariate Extremes: a Wasserstein-Aitchison GAN approach](https://mlsanity.com/paper/2504.21438/) (2025)
- [A Kolmogorov-Arnold Neural Model for Cascading Extremes](https://mlsanity.com/paper/2505.13370/) (2025)
- [Extrapolation in Statistical Learning with Extreme Value Theory](https://mlsanity.com/paper/2605.01909/) (2026)
- [Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows](https://mlsanity.com/paper/2608.11544/) (2026)
- [Modelling and simulating spatial extremes by combining extreme value theory with generative adversarial networks](https://mlsanity.com/paper/2111.00267/) (2021)
- [Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling](https://mlsanity.com/paper/2507.09211/) (2025)
- [Extreme value forecasting using relevance-based data augmentation with deep learning models](https://mlsanity.com/paper/2510.02407/) (2025)
- [Resilient Load Forecasting under Climate Change: Adaptive Conditional Neural Processes for Few-Shot Extreme Load Forecasting](https://mlsanity.com/paper/2602.04609/) (2026)
- [Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models](https://mlsanity.com/paper/2605.18931/) (2026)
- [An Extreme Value Perspective on Learning Stress Laws](https://mlsanity.com/paper/2607.10700/) (2026)
- [Local Violation Certification for Linear Predict-Then-Optimize Pipelines](https://mlsanity.com/paper/2608.04474/) (2026)
- [TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement](https://mlsanity.com/paper/2608.11951/) (2026)
- [Cross-View Time-Frequency Diffusion for Extreme-Aware Time-Series Generation](https://mlsanity.com/paper/2610.17407/) (2026)

## Abstract (arXiv)

Mitigating the risk arising from extreme events is a fundamental goal with many applications, such as the modelling of natural disasters, financial crashes, epidemics, and many others. To manage this risk, a vital step is to be able to understand or generate a wide range of extreme scenarios. Existing approaches based on Generative Adversarial Networks (GANs) excel at generating realistic samples, but seek to generate typical samples, rather than extreme samples. Hence, in this work, we propose ExGAN, a GAN-based approach to generate realistic and extreme samples. To model the extremes of the training distribution in a principled way, our work draws from Extreme Value Theory (EVT), a probabilistic approach for modelling the extreme tails of distributions. For practical utility, our framework allows the user to specify both the desired extremeness measure, as well as the desired extremeness probability they wish to sample at. Experiments on real US Precipitation data show that our method generates realistic samples, based on visual inspection and quantitative measures, in an efficient manner. Moreover, generating increasingly extreme examples using ExGAN can be done in constant time (with respect to the extremeness probability τ), as opposed to the O(frac1τ) time required by the baseline approach.