A Dictionary of Closed-Form Kernel Mean Embeddings
Lists
Only you see this
Abstract
Kernel mean embeddings -- integrals of a kernel with respect to a probability distribution -- are essential in Bayesian quadrature, but also widely used in other computational tools for numerical integration or for statistical inference based on the maximum mean discrepancy. These methods often require, or are enhanced by, the availability of a closed-form expression for the kernel mean embedding. However, deriving such expressions can be challenging, limiting the applicability of kernel-based techniques when practitioners do not have access to a closed-form embedding. This paper addresses this limitation by providing a comprehensive dictionary of known kernel mean embeddings, along with practical tools for deriving new embeddings from known ones. We also provide a Python library that includes minimal implementations of the embeddings.
BibTeX
@misc{briol2025dictionary,
author = {François-Xavier Briol and Alexandra Gessner and Toni Karvonen and Maren Mahsereci},
title = {{A Dictionary of Closed-Form Kernel Mean Embeddings}},
year = {2025},
eprint = {2504.18830},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2504.18830},
}| Statistical computation with kernels | Warwick · 2018 |
| Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions | arXiv · 2016 |
| Consistent Kernel Mean Estimation for Functions of Random Variables | arXiv · 2016 |
| Kernel Mean Embedding of Distributions: A Review and Beyond | Found. Trends Mach. Learn · 2017 |
| Nyström Kernel Mean Embeddings | arXiv · 2022 |
| Characteristic Kernels and Infinitely Divisible Distributions | arXiv · 2014 |