Research map / Bandits and online learning / Online convex optimization and games
Regret Bounds for Online Kernel Selection in Continuous Kernel Space
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 |
|---|---|---|---|
| Use OKS-SPT instead of RRF | Online kernel selection · german | mistake rate (%): 31.140 ± 0.114 -> 29.920 ± 0.286 | Helped |
| Use OKS-TPS instead of RRF | Online kernel selection · german | mistake rate (%): 31.140 ± 0.114 -> 29.760 ± 0.270 | Helped |
| Use OKS-SPT instead of OKS | Online kernel selection · spambase | mistake rate (%): 34.355 ± 0.372 -> 28.436 ± 0.213 | Helped |
| Use OKS-TPS instead of OKS | Online kernel selection · spambase | mistake rate (%): 34.355 ± 0.372 -> 28.450 ± 0.188 | Helped |
| Use OKS-SPT instead of OKL-GD | Online kernel selection · mushrooms | mistake rate (%): 4.226 ± 0.910 -> 6.585 ± 0.246 | Hurt |
| Use OKS-TPS instead of OKL-GD | Online kernel selection · mushrooms | mistake rate (%): 4.226 ± 0.910 -> 3.139 ± 0.481 | Helped |
| Use OKS-SPT instead of OKS | Online kernel selection · a9a | mistake rate (%): 23.617 ± 0.127 -> 20.368 ± 0.659 | Helped |
| Use OKS-TPS instead of OKS | Online kernel selection · a9a | mistake rate (%): 23.617 ± 0.127 -> 22.379 ± 0.192 | Helped |
| Use OKS-SPT instead of OKL-GD | Online kernel selection · w7a | mistake rate (%): 2.975 ± 0.062 -> 2.675 ± 0.023 | Helped |
| Use OKS-TPS instead of OKL-GD | Online kernel selection · w7a | mistake rate (%): 2.975 ± 0.062 -> 2.631 ± 0.010 | Helped |
| Use OKS-SPT instead of RRF | Online kernel selection · ijcnn1 | mistake rate (%): 9.574 ± 0.001 -> 9.478 ± 0.003 | Helped |
| Use OKS-TPS instead of RRF | Online kernel selection · ijcnn1 | mistake rate (%): 9.574 ± 0.001 -> 9.440 ± 0.002 | Helped |
Closest papers by meaning
- Improved Kernel Alignment Regret Bound for Online Kernel Learning (AAAI 2023 · similarity 0.92)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.88)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.88)
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization (NeurIPS 2026 · similarity 0.87)
- On the Necessity of Collaboration for Online Model Selection with Decentralized Data (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.