Research map / Learning theory and algorithms / Sample complexity
f-GANs in an Information Geometric Nutshell
Richard Nock, Zac Cranko, Aditya K Menon, Lizhen Qu, Robert C. Williamson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Vary generator μ-ReLU parameter μ | GAN with DCGAN on MNIST · MNIST | generation performance | Mixed |
| Vary generator μ-ReLU parameter μ | WGAN with MLP on MNIST · MNIST | generation performance | Improved |
| Vary generator μ-ReLU parameter μ | GAN with MLP on MNIST · MNIST | generation performance | Hurt |
| Replace ReLU with other tested generator activations | GAN architectures on MNIST · MNIST | generation performance | Mixed |
| Replace the sigmoid discriminator link with the Matsushita link | GAN with DCGAN on MNIST · MNIST | generation performance | Improved |
| Use the Matsushita link instead of no link | WGAN with DCGAN on MNIST · MNIST | generation performance | No clear effect |
Closest papers by meaning
- A Convex Duality Framework for GANs (NeurIPS 2018 · similarity 0.89)
- Approximation and Convergence Properties of Generative Adversarial Learning (NeurIPS 2017 · similarity 0.89)
- The Numerics of GANs (NeurIPS 2017 · similarity 0.89)
- Variational Annealing of GANs: A Langevin Perspective (ICML 2019 · similarity 0.88)
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step (ICLR 2018 · similarity 0.88)
- The GAN is dead; long live the GAN! A Modern GAN Baseline (NeurIPS 2024 · similarity 0.87)
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.
