Research map / Learning theory and algorithms / Kernels and regression theory
Randomized Kernel Selection With Spectra of Multilevel Circulant Matrices
Lizhong Ding, Shizhong Liao, Yong Liu, Peng Yang, Xin Gao
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 |
|---|---|---|---|
| replace kernel-matrix criterion (KTA) with randomized MCM-spectrum criterion | LSSVM kernel selection · adult | selection time (s): 4287.95 -> 61.02 | Improved |
| replace kernel-matrix criterion (KTA) with randomized MCM-spectrum criterion | LSSVM kernel selection · adult | test accuracy (%): 84.72 -> 84.17 | No clear effect |
| replace 5-fold CV with randomized criteria | LSSVM kernel selection · thyroid | selection time (s): 4761.78 -> 8.65 | Improved |
| randomized criteria scale where classic criteria run out of memory | LSSVM kernel selection · skin (245057 examples) | feasibility | Improved |
| use MCM spectrum KTA(v) instead of direct stack of random features KTA(Z) (ablation) | KTA criterion · mushrooms, D=500 | accuracy (%): 93.47 -> 98.83 | Improved |
| use MCM spectrum KTA(v) instead of direct stack of random features KTA(Z) (ablation) | KTA criterion · thyroid, D=100 | accuracy (%): 98.72 -> 98.36 | No clear effect |
| use MCM spectrum KTA(v) instead of direct stack KTA(Z) (ablation) | KTA criterion · thyroid/coil2000/penbased, D=100 | selection time (s) | Mixed |
| increase random feature count D beyond 100 (ablation) | randomized criteria · Table 1 datasets | accuracy | No clear effect |
Closest papers by meaning
- Learning Kernels with Random Features (NeurIPS 2016 · similarity 0.88)
- TRF: Learning Kernels with Tuned Random Features (AAAI 2022 · similarity 0.88)
- Learning Adaptive Random Features (AAAI 2019 · similarity 0.87)
- Approximate Kernel Selection with Strong Approximate Consistency (AAAI 2019 · similarity 0.87)
- Infinite Kernel Learning: Generalization Bounds and Algorithms (AAAI 2017 · similarity 0.87)
- Multi-View Randomized Kernel Classification via Nonconvex Optimization (AAAI 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.
