Noise-free sampling algorithms via regularized Wasserstein proximals

DOI10.1007/S40687-024-00479-2MaRDI QIDQ6644953zbMATH OpenFDO

Authors Stanley Osher, Wuchen Li

Publication date 28 November 2024

Published in Research in the Mathematical Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S40687-024-00479-2

zbMATH Keywords

MCMCsamplingscore approximationWasserstein proximal

Mathematics Subject Classification ID

Nonparametric inference (62G99) Monte Carlo methods (65C05)

Recommendations

• Analysis of Langevin Monte Carlo via convex optimization
• Kinetic Langevin MCMC sampling without gradient Lipschitz continuity -- the strongly convex case
• Higher order Langevin Monte Carlo algorithm
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions

Cites work

• A blob method for diffusion
• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• Accelerated information gradient flow
• An introduction to MCMC for machine learning
• Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
• Computable bounds for geometric convergence rates of Markov chains
• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Estimation of non-normalized statistical models by score matching
• Exponential convergence of Langevin distributions and their discrete approximations
• Handbook of Markov Chain Monte Carlo
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Hit-and-Run Algorithms for Generating Multivariate Distributions
• scientific article; zbMATH DE number 51724 (Why is no real title available?)
• Kernel density estimation via diffusion
• Mean field simulation for Monte Carlo integration
• Nonparametric density estimation for high-dimensional data -- algorithms and applications
• Nonparametric kernel density estimation and its computational aspects
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Proximal Markov chain Monte Carlo algorithms
• Rates of convergence of the Hastings and Metropolis algorithms
• Robust kernel density estimation
• Statistical Physics of Particles
• Stochastic Liouville Equations
• THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
• The Variational Formulation of the Fokker--Planck Equation
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Variable kernel density estimation

Cited in

(2)

• Tensor train based sampling algorithms for approximating regularized Wasserstein proximal operators
• Score-based deterministic density sampling

This page was built for publication: Noise-free sampling algorithms via regularized Wasserstein proximals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6644953)