Research map / Adversarial robustness and security / Attacks on text and graphs
Towards Principled Methods for Training 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 |
|---|---|---|---|
| Train the discriminator closer to optimality with the original cost function | DCGAN generator updates · DCGAN, generator after 1, 10, and 25 epochs | generator gradient norm: 5 orders of magnitude after 4000 discriminator iterations | Hurt |
| Train the discriminator closer to optimality with the -log D cost function | DCGAN generator updates · DCGAN, generator after 1, 10, and 25 epochs | sample quality | Hurt |
| Train the discriminator closer to optimality with the -log D cost function | DCGAN generator updates · DCGAN, generator after 1, 10, and 25 epochs | generator gradient norm | Hurt |
| Train a discriminator from scratch on a fixed generator | DCGAN · DCGAN, generator after 1, 10, and 25 epochs | discriminator accuracy: 1 | Helped |
Closest papers by meaning
- Training Generative Adversarial Networks by Solving Ordinary Differential Equations (NeurIPS 2020 · similarity 0.92)
- Dynamically Grown Generative Adversarial Networks (AAAI 2021 · similarity 0.92)
- Unrolled Generative Adversarial Networks (ICLR 2017 · similarity 0.91)
- On Stabilizing Generative Adversarial Training With Noise (CVPR 2019 · similarity 0.91)
- An Online Learning Approach to Generative Adversarial Networks (ICLR 2018 · similarity 0.91)
- Progressive Growing of GANs for Improved Quality, Stability, and Variation (ICLR 2018 · 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.