AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity

Shuxiao Chen, Hangfeng He, Weijie Su

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 7 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
Add label-aware higher-order regressionCNTK · CIFAR-10 binary classificationtest accuracy (Avg): 85.91 -> 86.95Improved
Add label-aware higher-order regressionCNTK · CIFAR-10 multi-class classificationtest accuracy (Avg): 52.44 -> 54.38Improved
Add label-aware higher-order regressionNTK · CIFAR-10 train-train, frog vs shiplocal elasticity RR: 63.83 -> 66.62Improved
Add label-aware higher-order regressionNTK · CIFAR-10 test-train, frog vs shiplocal elasticity RR: 63.76 -> 66.53Improved
Approximate the time-varying kernel using the NTH constructionNTK · Neural tangent hierarchy approximationapproximation errorImproved

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