Regularized Stein variational gradient flow

DOI10.1007/S10208-024-09663-WMaRDI QIDQ6936088zbMATH OpenFDO

Authors Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, Jianfeng Lu

Publication date 2 September 2025

Published in Foundations of Computational Mathematics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S10208-024-09663-W

zbMATH Keywords

convergence to equilibriummean-field analysisparticle-based samplingregularizationreproducing kernel Hilbert spaceStein variational gradient descentWasserstein gradient flow

Mathematics Subject Classification ID

Existence problems for PDEs: global existence, local existence, non-existence (35A01) Uniqueness problems for PDEs: global uniqueness, local uniqueness, non-uniqueness (35A02) Smoothness and regularity of solutions to PDEs (35B65) Weak solutions to PDEs (35D30) PDEs in connection with statistics (35Q62) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Bayesian problems; characterization of Bayes procedures (62C10) Bayesian inference (62F15) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75) Interacting particle systems in time-dependent statistical mechanics (82C22) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31)

Cites work

• \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
• A blob method for diffusion
• A blob method for the aggregation equation
• A Deterministic Approximation of Diffusion Equations Using Particles
• A practical guide to deterministic particle methods
• An introduction to the theory of reproducing kernel Hilbert spaces
• Analysis and geometry of Markov diffusion operators
• Deterministic diffusion of particles
• Hilbert space embeddings and metrics on probability measures
• scientific article; zbMATH DE number 3965636 (Why is no real title available?)
• scientific article; zbMATH DE number 2152346 (Why is no real title available?)
• Learning Theory
• Macroscopic and large scale phenomena: coarse graining, mean field limits and ergodicity. Based on the presentations at the summer school, Enschede, the Netherlands, 2012
• Measuring sample quality with diffusions
• Mercer’s Theorem, Feature Maps, and Smoothing
• On the optimality of kernel-embedding based goodness-of-fit tests
• On the rate of convergence in Wasserstein distance of the empirical measure
• Randomized sketches for kernels: fast and optimal nonparametric regression
• Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Sharp estimates for eigenvalues of integral operators generated by dot product kernels on the sphere
• Support Vector Machines
• The Bayesian update: variational formulations and gradient flows
• The Variational Formulation of the Fokker--Planck Equation
• Vlasov equations

This page was built for publication: Regularized Stein variational gradient flow

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6936088)