A Bayesian nonparametric approach to reconstruction and prediction of random dynamical systems

DOI10.1063/1.4990547zbMATH Open1388.37065arXiv1511.00154OpenAlexW2732728733WikidataQ38692614 ScholiaQ38692614MaRDI QIDQ4644231FDOQ4644231

Authors: Christos Merkatas, Konstantinos Kaloudis, Spyridon J. Hatjispyros 

Publication date: 30 May 2018

Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)

Abstract: We propose a Bayesian nonparametric mixture model for the reconstruction and prediction from observed time series data, of discretized stochastic dynamical systems, based on Markov Chain Monte Carlo methods (MCMC). Our results can be used by researchers in physical modeling interested in a fast and accurate estimation of low dimensional stochastic models when the size of the observed time series is small and the noise process (perhaps) is non-Gaussian. The inference procedure is demonstrated specifically in the case of polynomial maps of arbitrary degree and when a Geometric Stick Breaking mixture process prior over the space of densities, is applied to the additive errors. Our method is parsimonious compared to Bayesian nonparametric techniques based on Dirichlet process mixtures, flexible and general. Simulations based on synthetic time series are presented.

Full work available at URL: https://arxiv.org/abs/1511.00154

Recommendations

• Joint reconstruction and prediction of random dynamical systems under borrowing of strength
• Identification of non-linear time series via kernels
• A Bayesian nonparametric approach to dynamical noise reduction
• Bayesian Models for Non‐linear Autoregressions
• A Bayesian nonparametric approach to the approximation of the global stable manifold

zbMATH Keywords

time series dataMarkov chain, Monte Carlo method

Mathematics Subject Classification ID

Bayesian inference (62F15) Nonparametric estimation (62G05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Time series analysis of dynamical systems (37M10) Random measures (60G57) Generation, random and stochastic difference and differential equations (37H10)

Cites Work

• The Bayesian Choice
• Sampling the Dirichlet Mixture Model with Slices
• A Bayesian analysis of some nonparametric problems
• On the nature of turbulence
• Approximate entropy as a measure of system complexity.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Nonlinear Time Series Analysis
• On a class of Bayesian nonparametric estimates: I. Density estimates
• Adaptive Gibbs samplers and related MCMC methods
• Chaos in Dynamical Systems
• Geometric stick-breaking processes for continuous-time Bayesian nonparametric modeling
• A new Bayesian nonparametric mixture model
• Analysis of data sets of stochastic systems
• RECONSTRUCTION OF THE DETERMINISTIC DYNAMICS OF STOCHASTIC SYSTEMS
• Title not available (Why is that?)
• Homoclinic tangencies and non-normal Jacobians-effects of noise in nonhyperbolic chaotic systems
• Nonlinear noise reduction through Monte Carlo sampling
• Chaos, fractals and statistics
• Reconstructions and predictions of nonlinear dynamical systems: a hierarchical Bayesian approach
• Statistics, probability and chaos. With discussion and a rejoinder by the author
• Asymptotic derivation of Langevin-like equation with non-Gaussian noise and its analytical solution
• A Bayesian nonparametric study of a dynamic nonlinear model
• Influence of dynamical noise on time series generated by nonlinear maps
• Bayesian reconstructions and predictions of nonlinear dynamical systems via the hybrid Monte Carlo scheme
• Delay embedding in the presence of dynamical noise

Cited In (17)

• Bayesian reconstructions and predictions of nonlinear dynamical systems via the hybrid Monte Carlo scheme
• Title not available (Why is that?)
• System identification using autoregressive Bayesian neural networks with nonparametric noise models
• Bayesian model selection using automatic relevance determination for nonlinear dynamical systems
• Identification and prediction of stochastic dynamical systems in a polynomial chaos basis
• A Bayesian method of parameter identification and prediction of states of linear stationary dynamical systems
• Bayesian deconvolution of functions in RKHS using MCMC techniques
• On the existence of proper stochastic Markov models for statistical reconstruction and prediction of chaotic time series
• Recursive Bayesian algorithm with covariance resetting for identification of Box-Jenkins systems with non-uniformly sampled input data
• Bayesian non-parametric approaches to reconstructing oscillatory systems and the Nyquist limit
• Inference for differential equation models using relaxation via dynamical systems
• Joint reconstruction and prediction of random dynamical systems under borrowing of strength
• Quantifying Bayesian filter performance for turbulent dynamical systems through information theory
• Modeling of missing dynamical systems: deriving parametric models using a nonparametric framework
• Reconstructing latent dynamical noise for better forecasting observables
• A Bayesian nonparametric approach to dynamical noise reduction
• A Bayesian nonparametric approach to the approximation of the global stable manifold

This page was built for publication: A Bayesian nonparametric approach to reconstruction and prediction of random dynamical systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4644231)