A rigorous theory of conditional mean embeddings

DOI10.1137/19M1305069MaRDI QIDQ5037567zbMATH OpenOpenAlexFDO

Authors

Publication date 1 March 2022

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1912.00671

zbMATH Keywords

reproducing kernel Hilbert spaceGaussian measurekernel mean embeddingconditional mean embedding

Mathematics Subject Classification ID

General nonlinear regression (62J02) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Set functions and measures and integrals in infinite-dimensional spaces (Wiener measure, Gaussian measure, etc.) (28C20)

Abstract: Conditional mean embeddings (CMEs) have proven themselves to be a powerful tool in many machine learning applications. They allow the efficient conditioning of probability distributions within the corresponding reproducing kernel Hilbert spaces (RKHSs) by providing a linear-algebraic relation for the kernel mean embeddings of the respective joint and conditional probability distributions. Both centred and uncentred covariance operators have been used to define CMEs in the existing literature. In this paper, we develop a mathematically rigorous theory for both variants, discuss the merits and problems of each, and significantly weaken the conditions for applicability of CMEs. In the course of this, we demonstrate a beautiful connection to Gaussian conditioning in Hilbert spaces.

Recommendations

• Kernel Mean Embedding of Distributions: A Review and Beyond
• The linear conditional expectation in Hilbert space
• Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
• Hilbert space embeddings and metrics on probability measures
• Statistical inference with reproducing kernels

Cites work

• scientific article; zbMATH DE number 1668769 (Why is no real title available?)
• scientific article; zbMATH DE number 1713116 (Why is no real title available?)
• scientific article; zbMATH DE number 5957198 (Why is no real title available?)
• scientific article; zbMATH DE number 3146347 (Why is no real title available?)
• scientific article; zbMATH DE number 3576139 (Why is no real title available?)
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• scientific article; zbMATH DE number 5055767 (Why is no real title available?)
• scientific article; zbMATH DE number 3288044 (Why is no real title available?)
• A Hilbert Space Embedding for Distributions
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Eigendecompositions of transfer operators in reproducing kernel Hilbert spaces
• Generalized inverses and Douglas equations
• Hilbert space embeddings and metrics on probability measures
• Joint Measures and Cross-Covariance Operators
• Kernel Bayes' rule: Bayesian inference with positive definite kernels
• Kernel dimension reduction in regression
• On Majorization, Factorization, and Range Inclusion of Operators on Hilbert Space
• On operator ranges
• Separability of reproducing kernel spaces
• Support Vector Machines
• Theory of reproducing kernels and applications
• Universality, Characteristic Kernels and RKHS Embedding of Measures

Cited in

(7)

• The linear conditional expectation in Hilbert space
• Propagating uncertainty through system dynamics in reproducing kernel Hilbert space
• Critical imbeddings with multivariate rearrangements
• Conditional mean embedding and optimal feature selection via positive definite kernels
• Conditional expectation using compactification operators
• Convergence Rates for Learning Linear Operators from Noisy Data
• Adaptive joint distribution learning

This page was built for publication: A rigorous theory of conditional mean embeddings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037567)