AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels

Stefani Karp, Ezra Winston, Yuanzhi Li, Aarti Singh

NeurIPS 2021 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 3 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
increase background noise intensity from 0 to maxNTK · CIFAR-10 with ImageNet noiseaccuracy retained (%): 69.75Hurt
increase background noise intensity from 0 to maxWRN · CIFAR-10 with ImageNet noiseaccuracy retained (%): 98.97No clear effect
increase noise on CIFAR-Vehicles distractorsNTK · CIFAR-Vehiclesaccuracy retained (%): 76.37Hurt
increase ImageNet noise intensityNTK · CIFAR-2accuracy retained (%): 92.81Mixed
increase Gaussian noise stdev from 0 to 2NTK · CIFAR-2 Gaussianaccuracy retained (%): 85.54Hurt
increase Gaussian noise stdev from 0 to 2WRN · CIFAR-2 Gaussianaccuracy retained (%): 96.83No clear effect
increase NTK width factor (50, 100) on MNIST with Gaussian noisefinite-width NTK · MNIST with noisetest accuracyNo clear effect
use infinite-width NTK instead of finite-widthNTK · MNIST-20k with Gaussian noisetest accuracyNo clear effect
zero-noise comparison of CNN and NTKNTK · MNIST zero noisetest accuracyNo clear effect

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