Variance-aware estimation of kernel mean embedding

MaRDI QIDQ6982647zbMATH OpenFDO

Authors Geoffrey Wolfer, Pierre Alquier

Publication date 16 May 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/23-0161.html

zbMATH Keywords

maximum mean discrepancykernel mean embeddingdistribution learningempirical Bernstein

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Cites work

• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 3907465 (Why is no real title available?)
• scientific article; zbMATH DE number 3576139 (Why is no real title available?)
• 10.1162/15324430260185646
• 10.1162/153244303321897690
• A Bernstein-type inequality for \(U\)-statistics and \(U\)-processes
• A kernel two-sample test
• A sharp estimate of the binomial mean absolute deviation with applications
• Basic properties of strong mixing conditions. A survey and some open questions
• Concentration inequalities for functions of independent variables
• Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
• Estimating means of bounded random variables by betting
• Estimation of Copulas via Maximum Mean Discrepancy
• Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
• Foundations of machine learning
• General state space Markov chains and MCMC algorithms
• Interpolation of spatial data. Some theory for kriging
• Kernel mean shrinkage estimators
• Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
• Minimax estimation of kernel mean embeddings
• Mixing time and expansion of non-negatively curved Markov chains
• On concentration of self-bounding functions
• On domination of tail probabilities of (super)martingales: explicit bounds
• On the learnability of discrete distributions
• Probability Inequalities for Sums of Bounded Random Variables
• Rates of convergence for empirical processes of stationary mixing sequences
• Some Limit Theorems for Stationary Processes
• Stability bounds for stationary \(\varphi \)-mixing and \(\beta \)-mixing processes
• Sums and Gaussian vectors
• Tuning Bandit Algorithms in Stochastic Environments

This page was built for publication: Variance-aware estimation of kernel mean embedding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6982647)