Kernel Methods for Linear Discrete-Time Equations

2015/07/11 by Colonius, Fritz, Hamzi, Boumediene
#Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1507.03111

Abstract

Methods from learning theory are used in the state space of linear dynamical and control systems in order to estimate the system matrices. An application to stabilization via algebraic Riccati equations is included. The approach is illustrated via a series of numerical examples.

Related

• Kernel-Based Learning of Stable Nonlinear Systems
• Interpreting the dual Riccati equation through the LQ reproducing kernel
• A New Approach to Learning Linear Dynamical Systems
• Operator-valued Kernels and Control of Infinite dimensional Dynamic Systems
• Kernel-based models for system analysis