Minimax Parameter Estimation for Singular Linear Multivariate Models with Mixed Uncertainty
| Authors: | Siemenikhin Konstantin V., Moscow Aviation Institute, Russian Federation
Pankov Alexei R., Moscow Aviation Institute, Russian Federation |
|---|
| Topic: | 1.4 Stochastic Systems |
|---|
| Session: | Modeling and Estimation of Stochastic Systems |
|---|
| Keywords: | Parameter estimation, minimax techniques, uncertain linear systems, duality, convex programming, singular systems, regularization, Kalman filters. |
|---|
Abstract
The problem of minimax estimation is considered for the linear multivariate statistically indeterminate observation model with mixed uncertainty. It is shown that in the regular case the minimax estimate is defined explicitly via the solution of the dual optimization problem. For the singular models, the method of dual optimization is developed by means of using the Tikhonov regularization techniques. Several particular cases which are widely used in practice are also examined.
