Saved in:
Bibliographic Details
Main Authors: Lang, Quanjun, Lu, Jianfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10256
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917138040619008
author Lang, Quanjun
Lu, Jianfeng
author_facet Lang, Quanjun
Lu, Jianfeng
contents We analyze prediction error in stochastic dynamical systems with memory, focusing on generalized Langevin equations (GLEs) formulated as stochastic Volterra equations. We establish that, under a strongly convex potential, trajectory discrepancies decay at a rate determined by the decay of the memory kernel and are quantitatively bounded by the estimation error of the kernel in a weighted norm. Our analysis integrates synchronized noise coupling with a Volterra comparison theorem, encompassing both subexponential and exponential kernel classes. For first-order models, we derive moment and perturbation bounds using resolvent estimates in weighted spaces. For second-order models with confining potentials, we prove contraction and stability under kernel perturbations using a hypocoercive Lyapunov-type distance. This framework accommodates non-translation-invariant kernels and white-noise forcing, explicitly linking improved kernel estimation to enhanced trajectory prediction. Numerical examples validate these theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10256
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Error Analysis of Generalized Langevin Equations with Approximated Memory Kernels
Lang, Quanjun
Lu, Jianfeng
Machine Learning
Numerical Analysis
Dynamical Systems
Probability
Primary 60H20, Secondary 45D05, 82C31
We analyze prediction error in stochastic dynamical systems with memory, focusing on generalized Langevin equations (GLEs) formulated as stochastic Volterra equations. We establish that, under a strongly convex potential, trajectory discrepancies decay at a rate determined by the decay of the memory kernel and are quantitatively bounded by the estimation error of the kernel in a weighted norm. Our analysis integrates synchronized noise coupling with a Volterra comparison theorem, encompassing both subexponential and exponential kernel classes. For first-order models, we derive moment and perturbation bounds using resolvent estimates in weighted spaces. For second-order models with confining potentials, we prove contraction and stability under kernel perturbations using a hypocoercive Lyapunov-type distance. This framework accommodates non-translation-invariant kernels and white-noise forcing, explicitly linking improved kernel estimation to enhanced trajectory prediction. Numerical examples validate these theoretical findings.
title Error Analysis of Generalized Langevin Equations with Approximated Memory Kernels
topic Machine Learning
Numerical Analysis
Dynamical Systems
Probability
Primary 60H20, Secondary 45D05, 82C31
url https://arxiv.org/abs/2512.10256