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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Increase the hidden-parameter range from λ=1 to λ=100 | Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.01 | relative training error: 0.9188 -> 1.9055e-06 | Improved |
| Increase the hidden-parameter range from λ=1 to λ=100 | Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.05 | relative training error: 0.6546 -> 7.5046e-08 | Improved |
| Increase the hidden-parameter range from λ=1 to λ=100 | Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.1 | relative training error: 0.2089 -> 7.2133e-08 | Improved |
| Increase the hidden-parameter range from λ=1 to λ=100 | Sigmoid random net (L=10000) · Gaussian target f(x;σ), σ=0.5 | relative training error: 1.1781e-05 -> 6.8683e-08 | No clear effect |
| Use λ=1 rather than λ=100 | Sigmoid random net · g(x)=0.5cos(22πx²)+0.5x² | approximation of high-frequency mode | Hurt |
| 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)+0.5x² | approximation performance | No clear effect |
Closest papers by meaning
- Neural Networks with Small Weights and Depth-Separation Barriers (NeurIPS 2020 · similarity 0.87)
- Gradient Descent Provably Optimizes Over-parameterized Neural Networks (ICLR 2019 · similarity 0.87)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.86)
- Neural Redshift: Random Networks are not Random Functions (CVPR 2024 · similarity 0.86)
- Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes (ICLR 2024 · similarity 0.86)
- How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers (ICML 2024 · similarity 0.86)
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.
