Research map / Learning theory and algorithms / Kernels and regression theory
Towards a Unified Analysis of Random Fourier 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 |
|---|---|---|---|
| sampling features proportional to approximate ridge leverage scores (leverage weighted RFF) instead of spectral measure (plain RFF) | random Fourier features for kernel ridge regression and SVM/KLR · CPU, KINEMATICS (regression); COD-RNA, COVTYPE (classification) | test RMSE / misclassification rate | Helped |
| sampling features from empirical ridge leverage score distribution instead of spectral measure | kernel ridge regression · theory (Corollary 1 vs Corollary 2) | required number of features | Helped |
| approximate leverage score sampling (Algorithm 1) with resampled features, versus plain RFF with same feature count | kernel ridge regression · real-world datasets | learning accuracy / prediction error | Helped |
| sampling distribution with Lipschitz loss (leverage vs plain RFF) for SVM/KLR | kernel SVM and kernel logistic regression · theory | required number of features for O(sqrt(lambda)) risk | Helped |
Closest papers by meaning
- Sharp Analysis of Random Fourier Features in Classification (AAAI 2022 · similarity 0.93)
- Learning Adaptive Random Features (AAAI 2019 · similarity 0.91)
- A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent (NeurIPS 2020 · similarity 0.91)
- TRF: Learning Kernels with Tuned Random Features (AAAI 2022 · similarity 0.90)
- Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees (ICML 2017 · similarity 0.90)
- Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing (NeurIPS 2024 · similarity 0.87)
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.