Variable Exponential Forgetting for Estimation of the Statistics of the Normal-Wishart Distribution with a Constant Precision
Authors:
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5094-5100
Abstract
The problem of estimating normal regression-type models with possibly time-varying regression parameters and constant noise precision is considered and examined from the Bayesian viewpoint. The solution we propose exploits a collaborative decision in order to face the incomplete model of parameter variations. Under this approach, a loss functional evaluating two prediction alternatives is constructed, which allows us to merge both alternatives, complying with the principles of optimization theory. Specifically, the posterior probability density function (pdf) and its flattened variant are combined by means of the geometric mean with automatically adjusted weights. The result is an automatic rescaling of the covariance matrix through the forgetting factor in response to empirically confirmed performance.Keywords
This publication has 24 references indexed in Scilit:
- Practical application of model identification based on ARX models with transfer functionsControl Engineering Practice, 2013
- Parameter tracking with partial forgetting methodInternational Journal of Adaptive Control and Signal Processing, 2011
- Use of Kullback–Leibler divergence for forgettingInternational Journal of Adaptive Control and Signal Processing, 2008
- Gauss Newton variable forgetting factor recursiveleast squares for time varying parameter trackingElectronics Letters, 2000
- On duality of regularized exponential and linear forgettingAutomatica, 1996
- On a general concept of forgettingInternational Journal of Control, 1993
- Identification of nonstationary stochastic systems using parallel estimation schemesIEEE Transactions on Automatic Control, 1990
- Restricted exponential forgetting in real-time identificationAutomatica, 1987
- Convergence and stability properties of an adaptive regulator with variable forgetting factorAutomatica, 1986
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951