Equilibrium distributions and stability analysis of Gaussian Process State Space Models

Gaussian Process State Space Models (GP-SSM) are a data-driven stochastic model class suitable to represent nonlinear dynamics. They have become increasingly popular in non-parametric modeling approaches since they provide not only a prediction of the system behavior but also an accuracy of the prediction. For the application of these models, the analysis of fundamental system properties is required. In this paper, we analyze equilibrium distributions and stability properties of the GP-SSM. The computation of equilibrium distributions is based on the numerical solution of a Fredholm integral equation of the second kind and is suitable for any covariance function. Besides, we show that the GP-SSM with squared exponential covariance function is always mean square bounded and there exists a set which is positive recurrent.

[1]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[2]  Agathe Girard,et al.  Dynamic systems identification with Gaussian processes , 2005 .

[3]  David J. Fleet,et al.  Gaussian Process Dynamical Models , 2005, NIPS.

[4]  A. J. Jerri.  Introduction to Integral Equations With Applications , 1985 .

[5]  Carl E. Rasmussen,et al.  Variational Gaussian Process State-Space Models , 2014, NIPS.

[6]  J. Stoer,et al.  Introduction to Numerical Analysis , 2002 .

[7]  Juš Kocijan,et al.  Modelling and Control of Dynamic Systems Using Gaussian Process Models , 2015 .

[8]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[9]  Nicholas R. Jennings,et al.  Adaptive home heating control through Gaussian process prediction and mathematical programming , 2011 .

[10]  J. Kocijan,et al.  Non-linear model predictive control for models with local information and uncertainties , 2008 .

[11]  Jonathan P. How,et al.  Bayesian nonparametric adaptive control of time-varying systems using Gaussian processes , 2013, 2013 American Control Conference.

[12]  C. Rasmussen,et al.  Gaussian Process Priors with Uncertain Inputs - Application to Multiple-Step Ahead Time Series Forecasting , 2002, NIPS.

[13]  Sandra Hirche,et al.  Synthesizing Anticipatory Haptic Assistance Considering Human Behavior Uncertainty , 2015, IEEE Transactions on Robotics.

[14]  David J. Fleet,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Gaussian Process Dynamical Model , 2007 .

[15]  Jus Kocijan,et al.  Evolving Gaussian process models for prediction of ozone concentration in the air , 2013, Simul. Model. Pract. Theory.

[16]  K. Atkinson.  The Numerical Solution of Integral Equations of the Second Kind , 1997 .

[17]  Sandra Hirche,et al.  Stability of Gaussian process state space models , 2016, 2016 European Control Conference (ECC).

[18]  Noriyuki Hori,et al.  A new discrete-time model for a van del Pol Oscillator , 2010, Proceedings of SICE Annual Conference 2010.

[19]  D. Sworder,et al.  Introduction to stochastic control , 1972 .