Contraction rate estimates of stochastic gradient kinetic Langevin integrators

DOI10.1051/M2AN/2024038MaRDI QIDQ6667313zbMATH OpenFDO

Authors Benedict Leimkuhler, Daniel Paulin, Peter A. Whalley

Publication date 20 January 2025

Published in European Series in Applied and Industrial Mathematics (ESAIM): Mathematical Modelling and Numerical Analysis (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1051/M2AN/2024038

zbMATH Keywords

Bayesian logistic regressionBrunger-Brooks-Karpluscontractive numerical methodkinetic Langevin dynamicsMCMC samplingMNIST classificationstochastic gradientstochastic Verletunderdamped Langevin dynamicsWasserstein convergence

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Numerical solutions to stochastic differential and integral equations (65C30) Numerical analysis or methods applied to Markov chains (65C40)

Recommendations

• Contraction and convergence rates for discretized kinetic Langevin dynamics
• Kinetic Langevin MCMC sampling without gradient Lipschitz continuity -- the strongly convex case
• Couplings and quantitative contraction rates for Langevin dynamics
• Langevin dynamics with general kinetic energies

Cites work

• A maximal coupling for Markov chains
• A Stochastic Approximation Method
• Almost sure contraction for diffusions on \(\mathbb{R}^d\). Application to generalized Langevin diffusions
• Analysis of Langevin Monte Carlo via convex optimization
• Complexity of randomized algorithms for underdamped Langevin dynamics
• Contraction and convergence rates for discretized kinetic Langevin dynamics
• Contractivity of Runge-Kutta methods for convex gradient systems
• Control variates for stochastic gradient MCMC
• Convergence of Langevin MCMC in KL-divergence
• Coupling and convergence for Hamiltonian Monte Carlo
• Couplings and quantitative contraction rates for Langevin dynamics
• Couplings for Andersen dynamics
• Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
• Exponential convergence of Langevin distributions and their discrete approximations
• Global contractivity for Langevin dynamics with distribution-dependent forces and uniform in time propagation of chaos
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 7626757 (Why is no real title available?)
• scientific article; zbMATH DE number 3429908 (Why is no real title available?)
• Long time accuracy of Lie-Trotter splitting methods for Langevin dynamics
• Mixing time guarantees for unadjusted Hamiltonian Monte Carlo
• Molecular dynamics and the accuracy of numerically computed averages
• Molecular dynamics. With deterministic and stochastic numerical methods
• Multivariate output analysis for Markov chain Monte Carlo
• Nonasymptotic bounds for sampling algorithms without log-concavity
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Numerical integration of the Langevin equation: Monte Carlo simulation
• On explicit L^2-convergence rate estimate for underdamped Langevin dynamics
• On sampling from a log-concave density using kinetic Langevin diffusions
• Optimal Transport
• Products of Random Matrices
• Products of random matrices: dimension and growth in norm
• Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
• Rational construction of stochastic numerical methods for molecular sampling
• Speeding Up MCMC by Efficient Data Subsampling
• Stochastic gradient Markov chain Monte Carlo
• Stochastic Problems in Physics and Astronomy
• Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
• The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• The zig-zag process and super-efficient sampling for Bayesian analysis of big data
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient

Cited in

(9)

• Contraction and convergence rates for discretized kinetic Langevin dynamics
• Appropriate state-dependent friction coefficient accelerates kinetic Langevin dynamics
• Constrained dynamics, stochastic numerical methods and the modeling of complex systems. Abstracts from the workshop held May 26--31, 2024
• HMC and underdamped Langevin united in the unadjusted convex smooth case
• Estimates of the numerical density for stochastic differential equations with multiplicative noise
• Piecewise deterministic sampling with splitting schemes
• Unbiased kinetic Langevin Monte Carlo with inexact gradients
• On the computational cost of Stochastic Gradient Langevin Dynamics
• Theoretical guarantees for stochastic gradient Langevin dynamics

This page was built for publication: Contraction rate estimates of stochastic gradient kinetic Langevin integrators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6667313)