Research map / Probabilistic and scientific modeling / Variational and generative sampling
Consistent Kernel Mean Estimation for Functions of Random Variables
Carl-Johann Simon-Gabriel, Adam Scibior, Ilya O Tolstikhin, Bernhard Schölkopf
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 a reduced set (weighted, dependent-point) KME estimator of the marginal embeddings instead of i.i.d. samples when computing f(X) | kernel mean estimator of f(X) · synthetic arithmetic functions X*Y, X/Y, X^Y with Gaussian inputs | error of mean embedding estimate vs sample size N | No clear effect |
| replace the diagonal estimator (mu_1) with the reduced-set based estimator (mu_3) for functions of two variables (ablation) | kernel mean estimator of f(X,Y) · synthetic X*Y, X/Y, X^Y experiments | approximation error vs N | Improved |
| use U-statistic estimator (mu_2) over the diagonal estimator (mu_1) for functions of two variables (ablation) | kernel mean estimator of f(X,Y) · synthetic X*Y, X/Y, X^Y experiments | approximation error and variance vs N | Improved |
| requirement that kernel on input be c0-universal and weights bounded (sum |w_i| <= C) for consistency of f(X) estimator | consistency theorem for kernel mean estimator of f(X) · theoretical (compact spaces, continuous f) | consistency of embedding estimate | No clear effect |
Closest papers by meaning
- A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings (NeurIPS 2020 · similarity 0.91)
- Variance-Aware Estimation of Kernel Mean Embedding (JMLR 2025 · similarity 0.90)
- Kernel Quantile Embeddings and Associated Probability Metrics (ICML 2025 · similarity 0.90)
- On the Consistency of Kernel Methods with Dependent Observations (ICML 2024 · similarity 0.89)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.87)
- On Statistical Learning Theory for Distributional Inputs (ICML 2024 · similarity 0.86)
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.
