Research map / Learning theory and algorithms / Sample complexity
Approximability of Discriminators Implies Diversity 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 one-hidden-layer ReLU discriminators (linear-plus-ReLU features) instead of general Lipschitz functions when generators are Gaussians with bounded mean and covariance | Gaussian generator class · theoretical restricted approximability | approximability of W1 by IPM | Helped |
| Use discriminators with restricted approximability (tailored to generator class) instead of vanilla discriminators | WGAN on synthetic 2D datasets · Swiss roll and unit circle | correlation of IPM with Wasserstein distance | No clear effect |
Closest papers by meaning
- Don't let your Discriminator be fooled (ICLR 2019 · similarity 0.90)
- Dual Discriminator Generative Adversarial Nets (NeurIPS 2017 · similarity 0.90)
- On the Discrimination-Generalization Tradeoff in GANs (ICLR 2018 · similarity 0.90)
- Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions (ICLR 2022 · similarity 0.90)
- Mixed batches and symmetric discriminators for GAN training (ICML 2018 · similarity 0.90)
- Discriminative Forests Improve Generative Diversity for Generative Adversarial Networks (AAAI 2024 · similarity 0.88)
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.