Controlling moments with kernel Stein discrepancies

DOI10.1214/25-AAP2206MaRDI QIDQ6890857zbMATH OpenFDO

Authors Heishiro Kanagawa, Alessandro Barp, Arthur Gretton, Lester Mackey

Publication date 2 December 2025

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/25-AAP2206

zbMATH Keywords

Bayesian computationkernel Stein discrepanciesMarkov chain Monte Carlo methodreproducing kernel

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Central limit and other weak theorems (60F05) Computational methods in Markov chains (60J22) Approximations to statistical distributions (nonasymptotic) (62E17) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A kernel Stein test for comparing latent variable models
• A kernel two-sample test
• An introduction to sequential Monte Carlo
• Approximation Theorems of Mathematical Statistics
• Control functionals for Monte Carlo integration
• Controlling moments with kernel Stein discrepancies
• Exponential contraction in Wasserstein distances for diffusion semigroups with negative curvature
• Fundamentals of Stein's method
• Global divergence theorems in nonlinear PDEs and geometry
• scientific article; zbMATH DE number 3951715 (Why is no real title available?)
• scientific article; zbMATH DE number 3438144 (Why is no real title available?)
• scientific article; zbMATH DE number 2152346 (Why is no real title available?)
• Integral Probability Metrics and Their Generating Classes of Functions
• Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
• Matrix-valued kernels for shape deformation analysis
• Measuring sample quality with diffusions
• Multivariate Stein factors for a class of strongly log-concave distributions
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• On the Asymptotic Distribution of Differentiable Statistical Functions
• Optimal thinning of MCMC output
• Real Analysis and Probability
• Reflection couplings and contraction rates for diffusions
• Robust generalised Bayesian inference for intractable likelihoods
• Scattered Data Approximation
• Sequential Monte Carlo Samplers
• Sous-espaces d'espaces vectoriels topologiques et noyaux associés. (Noyaux reproduisants.)
• Stein's method meets computational statistics: a review of some recent developments
• The Speed of Mean Glivenko-Cantelli Convergence
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Theory of Reproducing Kernels
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM

Cited in

(1)

• Controlling moments with kernel Stein discrepancies

This page was built for publication: Controlling moments with kernel Stein discrepancies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6890857)