Research map / Learning theory and algorithms / Kernels and regression theory
Gaussian process regression: Optimality, robustness, and relationship with kernel ridge regression
Wenjia Wang, Bing-Yi Jing
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 |
|---|---|---|---|
| impose an oversmoothed Matern correlation (m=3.3 vs true m0=1.6) with mu scaled as n^(-m/m0+1) | Gaussian process regression · Matern GP simulation, d=1 | convergence-rate slope: 0.7138 vs theoretical 0.6875 | No clear effect |
| impose an oversmoothed Matern correlation (m=3.0 vs true m0=2.0) | Gaussian process regression · Matern GP simulation, d=1 | convergence-rate slope: 0.7664 vs theoretical 0.7500 | No clear effect |
| impose an undersmoothed correlation (m=2.0 vs true m0=3.0) with mu=0.1 | Gaussian process regression · Matern GP simulation, d=1 | convergence-rate slope: 0.7856 vs theoretical 0.7500 | No clear effect |
Closest papers by meaning
- Kernel Packet: An Exact and Scalable Algorithm for Gaussian Process Regression with Matérn Correlations (JMLR 2022 · similarity 0.89)
- Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness (JMLR 2021 · similarity 0.89)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 2024 · similarity 0.87)
- A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression (NeurIPS 2024 · similarity 0.86)
- Error Bounds for Gaussian Process Regression Under Bounded Support Noise with Applications to Safety Certification (AAAI 2025 · similarity 0.86)
- Distributionally Robust Active Learning for Gaussian Process Regression (ICML 2025 · 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.
