Convergence rate determination for gradient-based adaptive estimators (Q1084367): Difference between revisions

The paper presents a method for deriving a lower bound on the exponential convergence rate of the homogeneous part of gradient-based adaptive parameter estimators. The convergence rate depends on the minimum eigenvalue of the covariance matrix of the given random process. A comparison is drawn between adaptive estimators and the experimental design criteria for nonadaptive system identification.