Research map / Learning theory and algorithms / Kernels and regression theory
Kernelized Cumulants: Beyond Kernel Mean Embeddings
Patric Bonnier, Harald Oberhauser, Zoltán Szabó
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 d(2) kernelized cumulant statistic instead of MMD | two-sample test · U[-1,1] vs mixture of uniforms with matched first three moments | test power | Improved |
| use CSIC instead of HSIC | independence test · uniform vs chi-square Y_0.5^2 and X | test power | Improved |
| use d(2) instead of MMD | two-sample test · Seoul bicycle data, winter vs fall | test power | Improved |
| use d(2) instead of MMD under the null (winter vs winter) | two-sample test · Seoul bicycle data | Type I error: 5-10 | No clear effect |
| use CSIC instead of HSIC at very low sample sizes | independence test · Sao Paulo traffic data | test power | No clear effect |
| use CSIC instead of HSIC at larger sample sizes | independence test · Sao Paulo traffic data | test power | Improved |
| use d(3) instead of MMD at very small sample sizes | two-sample test · Sao Paulo traffic, slow vs fast traffic | test power | No clear effect |
| use d(3) instead of MMD at larger sample sizes | two-sample test · Sao Paulo traffic, slow vs fast traffic | test power | Improved |
Closest papers by meaning
- Kernel Quantile Embeddings and Associated Probability Metrics (ICML 2025 · similarity 0.88)
- Towards Unified Native Spaces in Kernel Methods (JMLR 2025 · similarity 0.87)
- Nyström Kernel Mean Embeddings (ICML 2022 · similarity 0.87)
- Reproducing kernel Hilbert C*-module and kernel mean embeddings (JMLR 2021 · similarity 0.87)
- A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings (NeurIPS 2020 · similarity 0.87)
- Gaussian Mixture Models in Hilbert Spaces via Kernel Methods (NeurIPS 2026 · 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.
