Research map / Bandits and online learning / Online convex optimization and games
Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression
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 NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · parkinson | MSE: 0.05553 ± 0.00024 -> 0.05514 ± 0.00008 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · elevators | MSE: 0.00452 ± 0.00018 -> 0.00284 ± 0.00005 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · cpusmall | MSE: 0.01166 ± 0.00080 -> 0.00703 ± 0.00024 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · bank | MSE: 0.01663 ± 0.00014 -> 0.01306 ± 0.00004 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · ailerons | MSE: 0.00320 ± 0.00007 -> 0.00288 ± 0.00001 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · calhousing | MSE: 0.02436 ± 0.00010 -> 0.02215 ± 0.00011 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · year | MSE: 0.01370 ± 0.00004 -> 0.01243 ± 0.00001 | Helped |
| Use NONS-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · TomsHardware | MSE: 0.00054 ± 0.00001 -> 0.00043 ± 0.00000 | Helped |
| Use AOGD-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · parkinson | MSE: 0.05553 ± 0.00024 -> 0.05988 ± 0.00018 | Hurt |
| Use AOGD-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · elevators | MSE: 0.00452 ± 0.00018 -> 0.00534 ± 0.00003 | Hurt |
| Use AOGD-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · cpusmall | MSE: 0.01166 ± 0.00080 -> 0.01330 ± 0.00006 | Hurt |
| Use AOGD-ALD instead of the strongest reported baseline, CON-KONS | Online kernel regression · bank | MSE: 0.01663 ± 0.00014 -> 0.01915 ± 0.00009 | Hurt |
Closest papers by meaning
- Improved Kernel Alignment Regret Bound for Online Kernel Learning (AAAI 2023 · similarity 0.91)
- Regret Bounds for Online Kernel Selection in Continuous Kernel Space (AAAI 2021 · similarity 0.91)
- Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation (NeurIPS 2017 · similarity 0.90)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.89)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.89)
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization (NeurIPS 2026 · similarity 0.89)
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.