Research map / Learning theory and algorithms / Sample complexity
A Convex Duality Framework for 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 |
|---|---|---|---|
| Replace discriminator batch normalization with spectral normalization | DCGAN · LSUN-bedroom | sample quality | Helped |
| Replace discriminator batch normalization with spectral normalization | DCGAN · LSUN-bedroom | training stability | Helped |
| Add spectral normalization to the discriminator | DCGAN · CelebA | sample quality | Helped |
| Add gradient penalty to the discriminator | DCGAN · CelebA | sample quality | Helped |
| Adversarially train the discriminator using WRM | DCGAN · CelebA | sample quality | Helped |
| Apply Lipschitz regularization or adversarial training to the discriminator | DCGAN · MNIST, CelebA, and LSUN | sample quality | Helped |
Closest papers by meaning
- Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions (ICLR 2022 · similarity 0.94)
- TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN (ICLR 2018 · similarity 0.93)
- Dualing GANs (NeurIPS 2017 · similarity 0.92)
- Approximation and Convergence Properties of Generative Adversarial Learning (NeurIPS 2017 · similarity 0.92)
- Dual Discriminator Generative Adversarial Nets (NeurIPS 2017 · similarity 0.91)
- A Neural Tangent Kernel Perspective of GANs (ICML 2022 · 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.