atlas

Research map / Image generation / GANs

A Neural Tangent Kernel Perspective of GANs

ICML 2022 · Image generation › GANs · approach: Generative adversarial network theory · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add non-zero bias to the ReLU discriminator (ablation)GANs with ReLU discriminators · 8-Gaussian distributiondistribution convergenceHelped
Use an infinite-width ReLU discriminator instead of a finite-width one (ablation)GANs with ReLU discriminators · 8-Gaussian distributiondistribution convergenceHelped
Use an NTK instead of the RBF kernel (ablation)Infinite-width GAN analysis · 8-Gaussian distributiondistribution convergenceHelped
Use an infinite-width IPM discriminator with a ReLU activationGANs · 8-Gaussian distributiondistribution matchHelped
Model finite-width discriminator training with its infinite-width NTKGAN discriminator analysis · Fixed distributionsdiscriminator behavior agreementHelped

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy