AI Paper Atlas

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

NeuralEF: Deconstructing Kernels by Deep Neural Networks

Zhijie Deng, Jiaxin Shi, Jun Zhu

ICML 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis · 2 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
Approximate the CNN-GP kernel using learned top eigenfunctionsMNIST image projections with logistic regression · MNIST testLR test accuracy: 78.00% -> 84.98% (polynomial kernel)Improved
Use NeuralEF-learned NTK projections instead of random featuresK-means clustering · CIFAR-10 test imagesaccuracy: 81.3% -> 97.5%Improved
Use NeuralEF-learned NTK projections instead of raw pixelsK-means clustering · CIFAR-10 test imagesaccuracy: 67.8% -> 97.5%Improved
Use NeuralEF to approximate the NTK in linearised Laplace approximationCIFAR-10 ResNet-20 LLA · CIFAR-10 testECE: 0.049 -> 0.016 (MAP); 0.026 -> 0.016 (Last-layer LLA)Improved
Use NeuralEF to approximate the NTK in linearised Laplace approximationCIFAR-10 ResNet-56 LLA · CIFAR-10 testECE: 0.024 -> 0.012 (Last-layer LLA)Improved
Use NeuralEF to approximate the NTK in linearised Laplace approximationCIFAR-10 ResNet-110 LLA · CIFAR-10 testECE: 0.019 -> 0.010 (Last-layer LLA)Improved
Use NeuralEF LLA rather than Last-layer LLACIFAR-10 ResNet-20 · CIFAR-10 testNLL: 0.264 -> 0.277Hurt
Use NeuralEF LLA rather than Last-layer LLACIFAR-10 ResNet-56 · CIFAR-10 testNLL: 0.231 -> 0.234Hurt
Use NeuralEF LLA rather than Last-layer LLACIFAR-10 ResNet-110 · CIFAR-10 testNLL: 0.233 -> 0.241Hurt
Approximate the NTK using only the top-10 eigenpairsNeuralEF kernel recovery · ResNet-20 binary-classifier NTK test kernelkernel approximation qualityHurt
Use NeuralEF instead of random features at similar resource consumptionNTK kernel approximation · ResNet-20 binary-classifier NTKapproximation qualityImproved

Later papers that compared with this method

1 later accepted paper reports NeuralEF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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