A new framework for extracting coarse-grained models from time series with multiscale structure

DOI10.1016/J.JCP.2015.05.002zbMATH Open1352.62136arXiv1409.1787OpenAlexW820024641MaRDI QIDQ727752FDOQ727752

S. Kalliadasis, G. A. Pavliotis, Sebastian Krumscheid

Publication date: 20 December 2016

Published in: Journal of Computational Physics (Search for Journal in Brave)

Abstract: In many applications it is desirable to infer coarse-grained models from observational data. The observed process often corresponds only to a few selected degrees of freedom of a high-dimensional dynamical system with multiple time scales. In this work we consider the inference problem of identifying an appropriate coarse-grained model from a single time series of a multiscale system. It is known that estimators such as the maximum likelihood estimator or the quadratic variation of the path estimator can be strongly biased in this setting. Here we present a novel parametric inference methodology for problems with linear parameter dependency that does not suffer from this drawback. Furthermore, we demonstrate through a wide spectrum of examples that our methodology can be used to derive appropriate coarse-grained models from time series of partial observations of a multiscale system in an effective and systematic fashion.

Full work available at URL: https://arxiv.org/abs/1409.1787

Recommendations

• Perturbation-based inference for diffusion processes: obtaining effective models from multiscale data
• Coarse-grained modeling of multiscale diffusions: the \(p\)-variation estimates
• Coarse-Graining Autonomous ODE Systems by Inducing a Separation of Scales: Practical Strategies and Mathematical Questions
• Discrete-time statistical inference for multiscale diffusions
• Parametrized invariant manifolds: a recipe for multiscale modeling?

zbMATH Keywords

chaotic dynamicshomogenizationstochastic differential equationsparametric inferencecoarse-grainingmultiscale diffusion

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Numerical solutions to stochastic differential and integral equations (65C30)

Cites Work

• Mixing: Properties and examples
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Nonlinear time series. Nonparametric and parametric methods
• Inference in hidden Markov models.
• Stochastic differential equations. An introduction with applications.
• Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
• A Tale of Two Time Scales
• Nonparametric statistics for stochastic processes. Estimation and prediction.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Statistical inference for ergodic diffusion processes.
• Nonlinearity and temporal dependence
• Multiscale Methods
• A note on diffusion limits of chaotic skew-product flows
• Extracting macroscopic dynamics: model problems and algorithms
• “Coarse” stability and bifurcation analysis using time-steppers: A reaction-diffusion example
• Maximum likelihood drift estimation for multiscale diffusions
• Handbook of Monte Carlo Methods
• Stochastic Processes and Applications
• Additive noise effects in active nonlinear spatially extended systems
• Fitting SDE models to nonlinear Kac-Zwanzig heat bath models
• Optimal control of multiscale systems using reduced-order models
• Analysis of multiscale methods for stochastic differential equations
• Parameter estimation for multiscale diffusions
• Numerical techniques for multi-scale dynamical systems with stochastic effects
• Optimal prediction and the Mori–Zwanzig representation of irreversible processes
• Title not available (Why is that?)
• An applied mathematics perspective on stochastic modelling for climate
• Adaptive sub-sampling for parametric estimation of Gaussian diffusions
• An optimization principle for deriving nonequilibrium statistical models of Hamiltonian dynamics
• Title not available (Why is that?)
• Maximum likelihood estimation for small noise multiscale diffusions
• Semiparametric Drift and Diffusion Estimation for Multiscale Diffusions
• Dimensional reduction in nonlinear filtering: a homogenization approach
• Diffusion estimation from multiscale data by operator eigenpairs
• LONG-TERM BEHAVIOUR OF LARGE MECHANICAL SYSTEMS WITH RANDOM INITIAL DATA
• Cell Mechanics
• Estimating eddy diffusivities from noisy Lagrangian observations
• Parametric estimation of stationary stochastic processes under indirect observability
• Estimation of space-dependent diffusions and potential landscapes from non-equilibrium data
• Multiscale Modelling and Inverse Problems
• Frequency Domain Estimation of Integrated Volatility for Itô Processes in the Presence of Market-Microstructure Noise
• Title not available (Why is that?)
• Perturbation-based inference for diffusion processes: Obtaining effective models from multiscale data
• Filtering the Maximum Likelihood for Multiscale Problems
• Convolutionless Nakajima–Zwanzig equations for stochastic analysis in nonlinear dynamical systems

Cited In (10)

• Parameter inference for degenerate diffusion processes
• Learning about structural errors in models of complex dynamical systems
• Perturbation-based inference for diffusion processes: Obtaining effective models from multiscale data
• Drift estimation of multiscale diffusions based on filtered data
• Eigenfunction martingale estimating functions and filtered data for drift estimation of discretely observed multiscale diffusions
• Statistical Learning of Nonlinear Stochastic Differential Equations from Nonstationary Time Series using Variational Clustering
• Rough McKean-Vlasov dynamics for robust ensemble Kalman filtering
• Manifold learning for accelerating coarse-grained optimization
• Ensemble Kalman inversion for sparse learning of dynamical systems from time-averaged data
• Path-space variational inference for non-equilibrium coarse-grained systems

This page was built for publication: A new framework for extracting coarse-grained models from time series with multiscale structure

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q727752)