On kernel structures for regularized system identification (II): a system theory perspective*. Issue 28 (2015)

• Record Type: Journal Article
• Authors: Chen, Tianshi; Ljung, Lennart
• Is Part Of: IFAC-PapersOnLine. Volume 48:Issue 28(2015)
• Page Start: 1041
• Page End: 1046
• Publication Date: 2015
• Subjects: System identification -- machine learning -- regularization methods -- kernel methods; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2015.12.268
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: In this companion paper, we will continue our discussions on the issue of kernel structure design and we will focus on the system theory perspective. In particular, we will study the stability, maximum entropy property, Markov property and model complexity of the recently introduced state space model induced kernel. These findings motivate a system theory perspective to understand the behavior of kernels and to construct more general kernels.