Research map / Learning theory and algorithms / Submodular and game algorithms
Finding Mixed Nash Equilibria of Generative Adversarial Networks
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 Mirror-GAN or Mirror-Prox-GAN instead of SGD | GAN training · 25 Gaussian mixtures | visual distribution fit | Helped |
| Use Mirror-GAN or Mirror-Prox-GAN instead of Adam | GAN training · 25 Gaussian mixtures | mode accuracy | Helped |
| Use Mirror-GAN or Mirror-Prox-GAN instead of Adam | GAN training · 25 Gaussian mixtures | variance capture | Helped |
| Use Mirror-GAN instead of RMSProp | GAN training · LSUN bedroom | visual image quality | Helped |
| Use Adam instead of Mirror-GAN | GAN training · LSUN bedroom | visual image quality | Hurt |
| Continue training with Adam | Adam · LSUN bedroom | training stability | Hurt |
Closest papers by meaning
- Do GANs always have Nash equilibria? (ICML 2020 · similarity 0.94)
- On Characterizing GAN Convergence Through Proximal Duality Gap (ICML 2021 · similarity 0.92)
- DO-GAN: A Double Oracle Framework for Generative Adversarial Networks (CVPR 2022 · similarity 0.92)
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step (ICLR 2018 · similarity 0.92)
- An Online Learning Approach to Generative Adversarial Networks (ICLR 2018 · similarity 0.91)
- Generative Adversarial Equilibrium Solvers (ICLR 2024 · 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.