AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

GEQ: Gaussian Kernel Inspired Equilibrium Models

Mingjie Li, Yisen Wang, Zhouchen Lin

NeurIPS 2023 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis · 0 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
replace linear kernel with Gaussian kernel (MOptEqs -> GEQ, 8M) (ablation)MOptEqs · CIFAR-100accuracy: 75.6 -> 78.2Improved
replace linear kernel with Gaussian kernel (MOptEqs -> GEQ, 8M)MOptEqs · CIFAR-10accuracy: 94.6 -> 95.6Improved
GEQ vs MOptEqsMOptEqs · ImageNet-100accuracy: 81.5 -> 83.9Improved
GEQ vs MOptEqsMOptEqs · ImageNetteaccuracy: 92.4 -> 93.2Improved
small GEQ (5M) vs ResNet-18 (10M)GEQ · CIFAR-10accuracy: 93.5 -> 94.8Improved
GEQ vs ResNet-50 with about half the parametersGEQ · ImageNet-100accuracy: 81.7 -> 83.9Improved
GEQ 8M vs ResNet-50 23MGEQ · CIFAR-100accuracy: 77.9 -> 78.2Improved
GEQ vs MOptEqs on unseen sub-classesMOptEqs · CIFAR-100 super-class unknown accuracyaccuracy: 77.4 -> 80.1Improved
GEQ vs MOptEqs on known sub-classesMOptEqs · CIFAR-100 super-class known accuracyaccuracy: 80.1 -> 80.9Improved
polynomial-kernel attentive module in MOptEqs (ablation)MOptEqs · CIFAR-100accuracy: 75.6 -> 75.1Hurt
sigmoid-kernel attentive module in MOptEqs (ablation)MOptEqs · CIFAR-100accuracy: 75.6 -> 76.1Improved
Gaussian kernel instead of sigmoid kernel (ablation)MOptEqs · CIFAR-100accuracy: 76.1 -> 78.2Improved

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