AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

Ming Li, Sho Sonoda, Feilong Cao, Yu Guang Wang, Jiye Liang

ICML 2023 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence

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 the hidden-parameter range from λ=1 to λ=100Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.01relative training error: 0.9188 -> 1.9055e-06Improved
Increase the hidden-parameter range from λ=1 to λ=100Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.05relative training error: 0.6546 -> 7.5046e-08Improved
Increase the hidden-parameter range from λ=1 to λ=100Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.1relative training error: 0.2089 -> 7.2133e-08Improved
Increase the hidden-parameter range from λ=1 to λ=100Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.5relative training error: 1.1781e-05 -> 6.8683e-08No clear effect
Use λ=1 rather than λ=100Sigmoid random net · g(x)=0.5cos(22πx²)+0.5x²approximation of high-frequency modeHurt
Remove neurons whose weights and biases lie in [-30,30] from the λ=100 network (ablation)Random net on g(x) · g(x)=0.5cos(22πx²)+0.5x²approximation performanceNo 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