Research map / Learning theory and algorithms / Kernels and regression theory
Orthogonal Random Features
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Replace Gaussian random projections with orthogonal random features | RFF · Gaussian kernel approximation | MSE | Helped |
| Use structured Hadamard-sign orthogonal projections instead of dense random projections | RFF · Gaussian kernel approximation | MSE | Helped |
| Use SORF rather than RFF or ORF | Kernel feature computation · gisette, D = 2d | speedup: 10 times | Helped |
| Replace the chi-distributed row scales with the scalar √d (ablation) | ORF · Real-world kernel approximation datasets | MSE | No clear effect |
| Reduce the Hadamard-diagonal blocks from three to two (ablation) | SORF · MNIST | MSE | No clear effect |
| Reduce the Hadamard-diagonal blocks from three to one (ablation) | SORF · MNIST | MSE | Hurt |
Closest papers by meaning
- A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent (NeurIPS 2020 · similarity 0.89)
- Simplex Random Features (ICML 2023 · similarity 0.88)
- Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees (ICML 2017 · similarity 0.88)
- On The Relative Error of Random Fourier Features for Preserving Kernel Distance (ICLR 2023 · similarity 0.88)
- Random matrices in service of ML footprint: ternary random features with no performance loss (ICLR 2022 · similarity 0.87)
- Random features for Grassmannian kernel approximation with bounded rank-one projections (NeurIPS 2026 · similarity 0.84)
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.