Research map / Optimization / Optimizers
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
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 separate discriminator and generator learning rates (TTUR) instead of equal learning rates | DCGAN · CelebA | FID: 21.4 -> 12.5 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | DCGAN · CIFAR-10 | FID: 37.7 -> 36.9 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | DCGAN · SVHN | FID: 21.4 -> 12.5 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | DCGAN · LSUN | FID: 70.4 -> 57.5 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | WGAN-GP · CIFAR-10 | FID: 29.3 -> 24.8 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | WGAN-GP · LSUN | FID: 20.5 -> 9.5 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | WGAN-GP · One Billion Word Benchmark 4-gram | JSD: 0.38 -> 0.35 | Helped |
| Use separate discriminator and generator learning rates (TTUR) instead of equal learning rates | WGAN-GP · One Billion Word Benchmark 6-gram | JSD: 0.77 -> 0.74 | Helped |
Closest papers by meaning
- On the Limitations of First-Order Approximation in GAN Dynamics (ICML 2018 · similarity 0.91)
- Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule (ICML 2023 · similarity 0.91)
- Finding Mixed Nash Equilibria of Generative Adversarial Networks (ICML 2019 · similarity 0.91)
- Projected GANs Converge Faster (NeurIPS 2021 · similarity 0.90)
- The GAN is dead; long live the GAN! A Modern GAN Baseline (NeurIPS 2024 · similarity 0.89)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.89)
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.