The harmonic analysis of kernel functions

被引：38
作者：
Zorzi, Mattia [1 ]
Chiuso, Alessandro [1 ]
机构：
[1] Univ Padua, Dipartimento Ingn Informaz, Via Gradenigo 6-B, I-35131 Padua, Italy
来源：
AUTOMATICA | 2018年 / 94卷
关键词：
System identification; Kernel-based methods; Power spectral density; Random features; SYSTEM-IDENTIFICATION; REGULARIZATION;
D O I：
10.1016/j.automatica.2018.04.015
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Kernel-based methods have been recently introduced for linear system identification as an alternative to parametric prediction error methods. Adopting the Bayesian perspective, the impulse response is modeled as a non-stationary Gaussian process with zero mean and with a certain kernel (i.e. covariance) function. Choosing the kernel is one of the most challenging and important issues. In the present paper we introduce the harmonic analysis of this non-stationary process, and argue that this is an important tool which helps in designing such kernel. Furthermore, this analysis suggests also an effective way to approximate the kernel, which allows to reduce the computational burden of the identification procedure. (C) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码：125 / 137
页数：13
相关论文
共 29 条
[11]   A Bayesian approach to sparse dynamic network identification [J].
Chiuso, Alessandro ;
Pillonetto, Gianluigi .
AUTOMATICA, 2012, 48 (08) :1553-1565
[12]  
Fraccaroli F., 2015, 54 IEEE C DEC CONTR
[13]   Transfer function and transient estimation by Gaussian process regression in the frequency domain [J].
Lataire, John ;
Chen, Tianshi .
AUTOMATICA, 2016, 72 :217-229
[14]  
Lindquist A., 2015, Linear Stochastic Systems: A Geometric Approach to Modeling, Estimation and Identification
[15]  
Pillonetto G., 2010, AM CONTR C
[16]   Regularized linear system identification using atomic, nuclear and kernel-based norms: The role of the stability constraint [J].
Pillonetto, Gianluigi ;
Chen, Tianshi ;
Chiuso, Alessandro ;
De Nicolao, Giuseppe ;
Ljung, Lennart .
AUTOMATICA, 2016, 69 :137-149
[17]   Kernel methods in system identification, machine learning and function estimation: A survey [J].
Pillonetto, Gianluigi ;
Dinuzzo, Francesco ;
Chen, Tianshi ;
De Nicolao, Giuseppe ;
Ljung, Lennart .
AUTOMATICA, 2014, 50 (03) :657-682
[18]   Prediction error identification of linear systems: A nonparametric Gaussian regression approach [J].
Pillonetto, Gianluigi ;
Chiuso, Alessandro ;
De Nicolao, Giuseppe .
AUTOMATICA, 2011, 47 (02) :291-305
[19]   A new kernel-based approach for linear system identification [J].
Pillonetto, Gianluigi ;
De Nicolao, Giuseppe .
AUTOMATICA, 2010, 46 (01) :81-93
[20]  
Rahimi A., 2007, Neural Information Processing Systems, V20, P1
123