Research map / Learning theory and algorithms / Sample complexity
Uniform Convergence Rates for Kernel Density Estimation
Heinrich Jiang
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 uniform (over x and bandwidth) VC-based Bernstein-type KDE bounds with bandwidth chosen optimally | KDE sup-norm estimation of Hölder densities · theory | convergence rate | Improved |
| Use the KDE argmax over data points as mode estimator with appropriate bandwidth | mode estimation · unimodal densities, finite samples | estimation rate | Improved |
| Use a KDE-based level-set estimator under Hausdorff metric | density level-set estimation · Hausdorff distance | convergence rate | Improved |
| Replace ||f||_inf with a data-based constant in the threshold (C tilde) for level-set estimation | density level-set estimator · Hausdorff metric | convergence rate | No clear effect |
| Restrict density estimation analysis to manifold dimension d_M instead of ambient dimension d | KDE on manifolds · manifold hypothesis | sup-norm error rate | Improved |
Closest papers by meaning
- Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension (ICML 2019 · similarity 0.91)
- SD-KDE: Score-Debiased Kernel Density Estimation (NeurIPS 2025 · similarity 0.90)
- Variational Weighting for Kernel Density Ratios (NeurIPS 2023 · similarity 0.88)
- Adaptive Greedy Algorithm for Moderately Large Dimensions in Kernel Conditional Density Estimation (JMLR 2022 · similarity 0.88)
- Even Faster Kernel Matrix Linear Algebra via Density Estimation (ICML 2026 · similarity 0.88)
- Dynamic Similarity Graph Construction with Kernel Density Estimation (ICML 2025 · similarity 0.84)
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.
