Asymptotic Marginal Likelihood on Linear Dynamical Systems

Takuto NAITO
Keisuke YAMAZAKI

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E97-D    No.4    pp.884-892
Publication Date: 2014/04/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E97.D.884
Type of Manuscript: PAPER
Category: Artificial Intelligence, Data Mining
Keyword: 
Bayesian learning,  Kalman filter,  time-series data analysis,  

Full Text: PDF(282.1KB)>>
Buy this Article



Summary: 
Linear dynamical systems are basic state space models literally dealing with underlying system dynamics on the basis of linear state space equations. When the model is employed for time-series data analysis, the system identification, which detects the dimension of hidden state variables, is one of the most important tasks. Recently, it has been found that the model has singularities in the parameter space, which implies that analysis for adverse effects of the singularities is necessary for precise identification. However, the singularities in the models have not been thoroughly studied. There is a previous work, which dealt with the simplest case; the hidden state and the observation variables are both one dimensional. The present paper extends the setting to general dimensions and more rigorously reveals the structure of singularities. The results provide the asymptotic forms of the generalization error and the marginal likelihood, which are often used as criteria for the system identification.


open access publishing via