Research map / Optimization / Nonconvex and smooth optimization
Smoothness and Stability in GANs
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 |
|---|---|---|---|
| Use a generator learning rate with γ/γ₀ between 1 and 1000 | Composite-regularized particle GAN · CIFAR-10 | FID | Helped |
| Use a learning rate much smaller than γ₀ | Composite-regularized particle GAN · CIFAR-10 | FID | Hurt |
| Use a learning rate much larger than γ₀ | Composite-regularized particle GAN · CIFAR-10 | FID | Hurt |
| Add spectral normalization and gradient penalties together rather than relying on spectral normalization alone | GAN training · GAN training stability | stability | Helped |
Closest papers by meaning
- Gradient descent GAN optimization is locally stable (NeurIPS 2017 · similarity 0.94)
- Understanding and Stabilizing GANs’ Training Dynamics Using Control Theory (ICML 2020 · similarity 0.93)
- Training Generative Adversarial Networks by Solving Ordinary Differential Equations (NeurIPS 2020 · similarity 0.93)
- Which Training Methods for GANs do actually Converge? (ICML 2018 · similarity 0.92)
- Unrolled Generative Adversarial Networks (ICLR 2017 · similarity 0.92)
- On Stabilizing Generative Adversarial Training With Noise (CVPR 2019 · similarity 0.91)
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.