Stability of Gaussian process state space models
Authors:
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2275-2281
Abstract
Gaussian Process State Space Models (GP-SSMs) are a non-parametric model class suitable to represent nonlinear dynamics. They become increasingly popular in data-driven modeling approaches, i.e. when no first-order physics-based models are available. Although a GP-SSM produces well-behaved approximations and gains increasing popularity, the fundamental system dynamics are just sparsely researched. In this paper, we present stability results for the GP-SSM depending on selected covariance function employing a deterministic point of view as widely done in the literature. The focus is set on the squared exponential function which is one of the most used covariance functions for nonlinear regression. We start with calculations according to the equilibrium points of GP-SSM and continue with conditions for stability.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Modelling and Control of Dynamic Systems Using Gaussian Process Models2016
- Bayesian nonparametric adaptive control of time-varying systems using Gaussian processes2013
- Model Reference Adaptive Control using Nonparametric Adaptive Elements2012
- On the estimation of transfer functions, regularizations and Gaussian processes—RevisitedAutomatica, 2012
- Non-linear model predictive control for models with local information and uncertaintiesTransactions of the Institute of Measurement and Control, 2008
- Predictive control of a gas–liquid separation plant based on a Gaussian process modelComputers & Chemical Engineering, 2007
- Dynamic systems identification with Gaussian processesMathematical and Computer Modelling of Dynamical Systems, 2005
- Nonlinear Predictive Control with a Gaussian Process Model2005
- Predictive control with Gaussian process models2004
- Polynomial Equations and Convex PolytopesThe American Mathematical Monthly, 1998