Research map / Learning theory and algorithms / Kernels and regression theory
Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels
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 |
|---|---|---|---|
| Select explicit features greedily by gradient correlation instead of using GLK | Kernel approximation · Year prediction | test error (%): 5.08 -> 4.78 | Helped |
| Select explicit features greedily rather than use EERF random features | Kernel approximation · Online news popularity | test error (%): 1.63% to 0.57% | Helped |
| Select explicit features greedily instead of using GLK | Kernel approximation · Online news popularity | test error (%): 0.14 -> 0.57 | Hurt |
| Select explicit features greedily instead of using GLK | Kernel approximation · Adult | test error (%): 15.22 -> 15.10 | Helped |
| Select explicit features greedily instead of using GK | Kernel approximation · Epileptic seizure recognition | test error (%): 2.82 -> 4.73 | Hurt |
Closest papers by meaning
- Random Features for Shift-Invariant Kernels with Moment Matching (AAAI 2017 · similarity 0.90)
- Quadrature-based features for kernel approximation (NeurIPS 2018 · similarity 0.89)
- Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning (ICML 2022 · similarity 0.88)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.86)
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.86)
- The optimality of kernel classifiers in Sobolev space (ICLR 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.