AI Paper Atlas

Research map / Optimization / Optimizers

Sinkhorn Natural Gradient for Generative Models

Zebang Shen, Zhenfu Wang, Alejandro Ribeiro, Hamed Hassani

NeurIPS 2020 · Optimization › Optimizers · approach: Natural gradient and Fisher approximations · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use SiNG instead of AdamDC-GAN generator · CelebAgenerator lossImproved
Use SiNG instead of SGD-type optimizersDC-GAN generator with a fixed encoder ground cost · CelebAgenerator lossImproved
Use SiNG instead of SGD-type optimizersDC-GAN generator with a fixed encoder ground cost · CIFAR-10generator lossImproved
Use SiNG instead of SGD-based optimizersDC-GAN · GAN image generationvisual qualityImproved
Use the kernelized Wasserstein natural gradient (KWNG)generative-model optimization · paper's experimental settingconvergenceHurt

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