Unadjusted Langevin algorithm for non-convex weakly smooth potentials

DOI10.1007/S40304-023-00350-WMaRDI QIDQ6942307zbMATH OpenFDO

Authors Dao Nguyen, Xin Dang, Yixin Chen

Publication date 19 August 2025

Published in Communications in Mathematics and Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S40304-023-00350-W

zbMATH Keywords

convexificationdiffusion processesKullback-Leibler divergencelog-Sobolev inequalityunadjusted Langevin algorithm

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Diffusion processes (60J60) Bayesian inference (62F15) Markov processes: estimation; hidden Markov models (62M05) Monte Carlo methods (65C05) Numerical solutions to stochastic differential and integral equations (65C30)

Cites work

• A note on Talagrand's transportation inequality and logarithmic Sobolev inequality
• Analysis of Langevin Monte Carlo via convex optimization
• Convergence of Langevin MCMC in KL-divergence
• Convergence rate of Riemannian Hamiltonian Monte Carlo and faster polytope volume computation
• Couplings and quantitative contraction rates for Langevin dynamics
• Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau
• Generalized spherical and simplicial coordinates
• Hit-and-run from a corner
• scientific article; zbMATH DE number 1619459 (Why is no real title available?)
• scientific article; zbMATH DE number 54145 (Why is no real title available?)
• scientific article; zbMATH DE number 3894218 (Why is no real title available?)
• scientific article; zbMATH DE number 7148060 (Why is no real title available?)
• scientific article; zbMATH DE number 3352023 (Why is no real title available?)
• Isoperimetric and analytic inequalities for log-concave probability measures
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Logarithmic Sobolev Inequalities
• Random gradient-free minimization of convex functions
• Sampling can be faster than optimization
• The geometry of logconcave functions and sampling algorithms
• The Variational Formulation of the Fokker--Planck Equation
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient

Cited in

(1)

• Weighted average iterated filtering using p-generalized Gaussian smoothing

This page was built for publication: Unadjusted Langevin algorithm for non-convex weakly smooth potentials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6942307)