Research map / Learning theory and algorithms / Kernels and regression theory
On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise
Johannes Teutsch, Oleksii Molodchyk, Marion Leibold, Timm Faulwasser, Armin Lederer
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 |
|---|---|---|---|
| use proposed uniform bound instead of Abbasi-Yadkori bound | Abbasi-Yadkori bound · bounded noise, n_x 1-3 | uncertainty region size | Improved |
| use proposed bound instead of Fiedler et al. with few data points | Fiedler et al. bound · bounded noise, low data | uncertainty region size: up to 7.5% | Hurt |
| use proposed bound instead of Fiedler et al. with many data points | Fiedler et al. bound · bounded noise, t up to 1000 | uncertainty region size | Improved |
| use proposed bound instead of Fiedler et al. in low-data safe control | Fiedler et al. bound · safe control, sub-Gaussian noise | success rate: <1.1% | Hurt |
| use proposed bound instead of Abbasi-Yadkori in safe control | Abbasi-Yadkori bound · safe control | success rate | Improved |
| use bounded-noise bound (b) instead of sub-Gaussian bound (a) at n_x=1 with large data | sub-Gaussian bound · bounded noise | uncertainty region size | Improved |
| use sub-exponential bound (c) instead of Chowdhury and Gopalan | Chowdhury and Gopalan bound · chi-squared noise | uncertainty region size: over two orders of magnitude | Improved |
| use sub-exponential bound (c) instead of the Proposition bound | Proposition bound · chi-squared noise | uncertainty region size: over an order of magnitude | Improved |
| use sub-exponential bound (c) in safe control instead of Proposition bound | Proposition bound · chi-squared noise safe control | success rate: 0% -> 71.6% | Improved |
Closest papers by meaning
- Optimal kernel regression bounds under energy-bounded noise (NeurIPS 2025 · similarity 0.92)
- Error Bounds for Gaussian Process Regression Under Bounded Support Noise with Applications to Safety Certification (AAAI 2025 · similarity 0.89)
- Regularized least squares learning with heavy-tailed noise is minimax optimal (NeurIPS 2025 · similarity 0.88)
- Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression (AAAI 2021 · similarity 0.87)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.87)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 2024 · similarity 0.85)
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.
