Maximum Entropy Kernels for System Identification

DOI10.1109/TAC.2016.2582642zbMATH Open1366.93669arXiv1411.5620OpenAlexW3103767811MaRDI QIDQ5282397FDOQ5282397

Authors: Francesca P. Carli, Tianshi Chen, Lennart Ljung 

Publication date: 27 July 2017

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Abstract: A new nonparametric approach for system identification has been recently proposed where the impulse response is modeled as the realization of a zero-mean Gaussian process whose covariance (kernel) has to be estimated from data. In this scheme, quality of the estimates crucially depends on the parametrization of the covariance of the Gaussian process. A family of kernels that have been shown to be particularly effective in the system identification framework is the family of Diagonal/Correlated (DC) kernels. Maximum entropy properties of a related family of kernels, the Tuned/Correlated (TC) kernels, have been recently pointed out in the literature. In this paper we show that maximum entropy properties indeed extend to the whole family of DC kernels. The maximum entropy interpretation can be exploited in conjunction with results on matrix completion problems in the graphical models literature to shed light on the structure of the DC kernel. In particular, we prove that the DC kernel admits a closed-form factorization, inverse and determinant. These results can be exploited both to improve the numerical stability and to reduce the computational complexity associated with the computation of the DC estimator.

Full work available at URL: https://arxiv.org/abs/1411.5620

Recommendations

• Maximum entropy vector kernels for MIMO system identification
• Nonparametric system identification by kernel methods
• Kernel entropy estimation for linear processes
• Kernel methods in system identification, machine learning and function estimation: a survey
• Maximum entropy principle in problems of identification of a class of nonstationary signals
• KERNEL ESTIMATION OF RESIDUAL ENTROPY
• Kernels for linear time invariant system identification
• Multivariate maximum entropy identification, transformation, and dependence
• Fast kernel entropy estimation and optimization

Mathematics Subject Classification ID

Bayesian inference (62F15) Density estimation (62G07) Estimation and detection in stochastic control theory (93E10) Identification in stochastic control theory (93E12)

Cited In (16)

• The occupation kernel method for nonlinear system identification
• Maximum entropy properties of discrete-time first-order stable spline kernel
• On embeddings and inverse embeddings of input design for regularized system identification
• Deterministic error bounds for kernel-based learning techniques under bounded noise
• When cannot regularization improve the least squares estimate in the kernel-based regularized system identification
• Regularized LTI system identification in the presence of outliers: a variational EM approach
• Maximum entropy vector kernels for MIMO system identification
• Sparse plus low rank network identification: a nonparametric approach
• On semiseparable kernels and efficient implementation for regularized system identification and function estimation
• Bayesian positive system identification: truncated Gaussian prior and hyperparameter estimation
• A shift in paradigm for system identification
• On kernel design for regularized LTI system identification
• On input design for regularized LTI system identification: power-constrained input
• On asymptotic properties of hyperparameter estimators for kernel-based regularization methods
• Kernel-based linear system identification: when does the representer theorem hold?
• Smoothing Splines and Rank Structured Matrices: Revisiting the Spline Kernel

This page was built for publication: Maximum Entropy Kernels for System Identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5282397)