Taming the interacting particle Langevin algorithm: the superlinear case

DOI10.1007/S00245-025-10269-ZMaRDI QIDQ6956519zbMATH OpenFDO

Authors Tim Johnston, Nikolaos Makras, Sotirios Sabanis

Publication date 18 July 2025

Published in Applied Mathematics and Optimization (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S00245-025-10269-Z

zbMATH Keywords

interacting particle systemsnon-asymptotic error estimatespolynomial growth conditionsstochastic optimizationtamed unadjusted Langevin algorithms

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Numerical solutions to stochastic differential and integral equations (65C30) Stochastic programming (90C15)

Cites work

• A note on tamed Euler approximations
• An introduction to infinite-dimensional analysis
• Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
• Euler approximations with varying coefficients: the case of superlinearly growing diffusion coefficients
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Higher order Langevin Monte Carlo algorithm
• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• Langevin dynamics based algorithm e-THO POULA for stochastic optimization problems with discontinuous stochastic gradient
• Log-concavity and strong log-concavity: a review
• Maximum Likelihood Algorithms for Generalized Linear Mixed Models
• Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• On explicit approximations for Lévy driven SDEs with super-linear diffusion coefficients
• On explicit order 1.5 approximations with varying coefficients: the case of super-linear diffusion coefficients
• Strong and weak divergence in finite time of Euler's method for stochastic differential equations with non-globally Lipschitz continuous coefficients
• Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients
• Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms
• The tamed unadjusted Langevin algorithm

This page was built for publication: Taming the interacting particle Langevin algorithm: the superlinear case

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6956519)