Higher order Langevin Monte Carlo algorithm

DOI10.1214/19-EJS1615zbMath1429.60006arXiv1808.00728MaRDI QIDQ2326072

Sotirios Sabanis, Ying Zhang

Publication date: 4 October 2019

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.00728

zbMATH Keywords

rate of convergenceMarkov chain Monte Carlomachine learningsampling problemsuper-linear coefficientshigher order algorithm

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Computational methods for problems pertaining to probability theory (60-08) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10)

Related Items (8)

Error estimates of the backward Euler-Maruyama method for multi-valued stochastic differential equations ⋮ Sublinear Convergence of a Tamed Stochastic Gradient Descent Method in Hilbert Space ⋮ Gradient-based adaptive importance samplers ⋮ Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization ⋮ Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms ⋮ On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case ⋮ Kinetic Langevin MCMC sampling without gradient Lipschitz continuity -- the strongly convex case ⋮ Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Euler approximations with varying coefficients: the case of superlinearly growing diffusion coefficients
• Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients
• A note on tamed Euler approximations
• Exponential convergence of Langevin distributions and their discrete approximations
• Introductory lectures on convex optimization. A basic course.
• On explicit order 1.5 approximations with varying coefficients: the case of super-linear diffusion coefficients
• On Milstein approximations with varying coefficients: the case of super-linear diffusion coefficients
• The tamed unadjusted Langevin algorithm
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Stochastic C-stability and B-consistency of explicit and implicit Milstein-type schemes
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Strong and weak divergence in finite time of Euler's method for stochastic differential equations with non-globally Lipschitz continuous coefficients
• Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
• Evaluating Derivatives
• Markov Chains and Stochastic Stability
• The tamed Milstein method for commutative stochastic differential equations with non-globally Lipschitz continuous coefficients
• Analysis and Geometry of Markov Diffusion Operators
• Evaluating higher derivative tensors by forward propagation of univariate Taylor series
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Optimal Transport

This page was built for publication: Higher order Langevin Monte Carlo algorithm