Research map / Optimization / Optimizers
Gradient descent GAN optimization is locally stable
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add discriminator-gradient-norm penalty to the generator update | WGAN · 2D uniform toy system | local convergence behavior | Helped |
| Use vanilla updates without the gradient penalty (ablation) | WGAN · 2D uniform toy system | local convergence behavior | Hurt |
| Add discriminator-gradient-norm penalty to the generator update | Traditional GAN · Eight Gaussians | mode coverage | Helped |
| Add discriminator-gradient-norm penalty to the generator update | DCGAN · Stacked MNIST | mode coverage | Helped |
| Use vanilla updates without the gradient penalty (ablation) | Traditional GAN · Eight Gaussians | mode coverage | Hurt |
| Use vanilla updates without the gradient penalty (ablation) | Traditional GAN · 2D uniform toy system | local convergence behavior | Helped |
Closest papers by meaning
- Smoothness and Stability in GANs (ICLR 2020 · similarity 0.94)
- Which Training Methods for GANs do actually Converge? (ICML 2018 · similarity 0.92)
- Training Generative Adversarial Networks by Solving Ordinary Differential Equations (NeurIPS 2020 · similarity 0.90)
- Improved Training of Wasserstein GANs (NeurIPS 2017 · similarity 0.90)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium (NeurIPS 2017 · similarity 0.90)
- Understanding and Stabilizing GANs’ Training Dynamics Using Control Theory (ICML 2020 · similarity 0.90)
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.