Research map / Learning theory and algorithms / Kernels and regression theory
Linear Kernel Tests via Empirical Likelihood for High-Dimensional Data
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 ELR-MMD instead of Lin-MMD | linear MMD two-sample test · Gaussian vs Laplacian, d=10-100 | rejection rate | Helped |
| use ELR-KSD instead of Lin-KSD | linear KSD goodness-of-fit test · Gaussian vs Laplacian, d=10-100 | rejection rate | Helped |
| increase number of samples n | ELR vs linear statistics · Gaussians N(0,I) vs N(0,vI), d=100 | rejection rate gap | Hurt |
| use ELR statistics instead of FSSD-opt | two/goodness-of-fit tests · Gaussians d=50,100 | rejection rate | Helped |
| increase FSSD test locations J to 10 and 50 | FSSD-opt · Gaussians d=10-100 | rejection rate | No clear effect |
| increase dimension d from 10 to 100 | FSSD-opt · Gaussian vs Laplacian | rejection rate | Hurt |
| use ELR statistics instead of FSSD-opt | linear tests · running time, d=100, n up to 14000 | time | Helped |
| use ELR statistics instead of Lin statistics | linear tests · Type I error, Gaussian and RBM | false rejection rate | No clear effect |
Closest papers by meaning
- A Kernel Test of Goodness of Fit (ICML 2016 · similarity 0.89)
- A Kernelized Stein Discrepancy for Goodness-of-fit Tests (ICML 2016 · similarity 0.88)
- Comparing distributions: $\ell_1$ geometry improves kernel two-sample testing (NeurIPS 2019 · similarity 0.88)
- Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample Tests (NeurIPS 2026 · similarity 0.86)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.85)
- DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing (NeurIPS 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.