AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

ICLR 2020 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 92 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 the number of Monte Carlo samplesNeural Tangents Monte Carlo kernel estimation · WideResNet kernel convergencedistance to empirical kernelHelped
Increase the network widening factorFinite-channel WideResNet · WideResNet kernel convergencedistance to infinite-width kernelHelped
Use a WideResNet rather than a convolutional or fully connected architectureInfinite-width NNGP or NTK inference · CIFAR-10performanceHelped
Increase the training-set sizeInfinite-width FC, convolutional, and WideResNet models · CIFAR-10performanceHelped
Distribute kernel computation across more acceleratorsNeural Tangents analytic kernel computation · 21-layer ReLU network with global average poolingtime per sampleHelped
Increase batch size for blocked covariance computationNeural Tangents analytic kernel computation · 21-layer ReLU network with global average poolingperformanceHelped

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