Research map / Image generation / GANs
EV-GAN: Simulation of extreme events with ReLU neural networks
Michaël Allouche, Stéphane Girard, Emmanuel Gobet
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the EV-GAN extreme-value generator parametrization instead of a classic GAN | GAN · Stock indices NKX (d=1) | MSLE(0.99): 1.381 -> 0.200 | Improved |
| use EV-GAN parametrization | GAN · Stock indices Europe (d=2) | MSLE(0.90): 3.860 -> 0.132 | Improved |
| use EV-GAN parametrization | GAN · Stock indices World (d=6) | AKE: 24.781 -> 3.533 | Improved |
| use EV-GAN parametrization | GAN · Stock indices Asia (d=3) | AKE: 9.760 -> 4.872 | Improved |
| use EV-GAN parametrization | GAN · Stock indices World (d=6) | MSLE(0.99): 5.000 -> 1.960 | Improved |
| use EV-GAN parametrization | GAN · Simulated Gumbel-Burr d=4 | MSLE(0.99) x100: 16.961 -> 5.990 | Improved |
| use EV-GAN parametrization | GAN · Simulated bivariate Burr margins, gamma=0.9 | tail-index slope: 0.131 -> 0.736 | Improved |
| use EV-GAN parametrization | GAN · Simulated bivariate Burr margins, gamma=0.9 | tail-index slope (margin 2): 0.115 -> 0.714 | Improved |
| use EV-GAN parametrization | GAN · Simulated Gumbel-Burr, 27 bivariate configurations | MSLE(0.99) | Improved |
| use EV-GAN parametrization | GAN · Simulated Gumbel-Burr, gamma in {0.5, 0.9} | AKE | Improved |
| use EV-GAN parametrization to scale dimension | GAN · Simulated d-variate Gumbel-Burr | max dimension with realistic margins: 8 -> 512 | Improved |
| increase dimension beyond 16 | EV-GAN · Simulated d-variate Gumbel-Burr dependence | lambda function fidelity | Hurt |
Closest papers by meaning
- ExGAN: Adversarial Generation of Extreme Samples (AAAI 2021 · similarity 0.90)
- Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions (ICML 2021 · similarity 0.88)
- How Well Generative Adversarial Networks Learn Distributions (JMLR 2021 · similarity 0.86)
- Variational Annealing of GANs: A Langevin Perspective (ICML 2019 · similarity 0.85)
- AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-Series Generation (AAAI 2023 · similarity 0.85)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
