Research map / Learning theory and algorithms / Kernels and regression theory
A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
Tin Sum Cheng, Aurelien Lucchi, Anastasis Kratsios, Ivan Dokmanić, David Belius
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 |
|---|---|---|---|
| Analyze in the L2(rho) eigenfunction basis instead of the RKHS basis | Finite-rank KRR test-error analysis · Under-parameterized finite-rank KRR | test-error bound sharpness | Improved |
| Allow regularization parameters independent of sample size | Finite-rank KRR test-error analysis · Under-parameterized finite-rank KRR | bound applicability | Improved |
| Add a high-probability lower bound alongside the upper bound | Finite-rank KRR test-error analysis · Under-parameterized finite-rank KRR | bound tightness | Improved |
| Use the derived bounds in the ridgeless limit | Finite-rank KRR test-error analysis · Ridgeless finite-rank KRR | bias-bound behavior | Improved |
| Restrict analysis to the under-parameterized regime | Finite-rank KRR test-error analysis · Finite-rank KRR | test-error bound sharpness | Improved |
Closest papers by meaning
- A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression (NeurIPS 2024 · similarity 0.90)
- Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum (ICML 2024 · similarity 0.90)
- Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning (NeurIPS 2025 · similarity 0.90)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.88)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 2024 · similarity 0.87)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.87)
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.
