Convergence Models for Lattice Joint Process Estimators and Least Squares Algorithms
نویسندگان
چکیده
A simple model characterizing the convergence properties of an adaptive digital lattice filter using gradient algorithms has been reported [ 11. This model is extended to the least mean square (LMS) lattice joint process estimator [SI, and to the least squares (LS) lattice and “fast” Kalman algorithms [9] -[16]. The models in each case are compared with computer simulation. The single-stage LMS lattice analysis presented in [l ] is also applied to the LS lattice. Results indicate that for stationary inputs, the LMS lattice and LS algorithms exhibit similar behavior. I.
منابع مشابه
Use of the Most Significant Autocorrelation Lags in Iterative ME Spectral Estimation
[ 7 ] R. S. Medaugh and L. J. Griffiths, “A comparison of two fast linear predictors,” in Proc. I981 IEEE ICASSP, Atlanta, GA, Mar. 1981, pp. 293-297. (81 M. L. Honig, “Convergence models for lattice joint process estimators and least squares algorithms,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-31, pp. 415-425, Apr. 1983. [ 9 ] M. S. Mueller, “On the rapid initial converge...
متن کاملNonlinear models with integrated regressors and convergence order results∗
This paper discusses complications that arise in the theory of nonlinear estimation in the presence of integrated regressors. A high-level asymptotic distribution theorem is established and convergence rates for nonlinear least squares estimators are derived.
متن کاملPenalized nonparametric mean square estimation of the coefficients of diffusion processes
We consider a one-dimensional diffusion process (Xt) which is observed at n+ 1 discrete times with regular sampling interval ∆. Assuming that (Xt) is strictly stationary, we propose nonparametric estimators of the drift and diffusion coefficients obtained by a penalized least squares approach. Our estimators belong to a finite-dimensional function space whose dimension is selected by a data-dri...
متن کاملLattice and QR Decomposition-Based Algorithms for Recursive Least Squares Adaptive Nonlinear Filters*
This paper presents a lattice structure for adaptive Volterra systems. The stucture is applicable to arbitrary planes of support of the Volterra kernels. A fast least squares lattice and a fast QR-lattice adaptive nonlinear filtering algorithms based on the lattice structure are also presented. These algorithms share the fast convergence property of fast least squares transversal Volterra filte...
متن کاملLeast Tail-Trimmed Squares for In...nite Variance Autoregressions
We develop a robust least squares estimator for autoregressions with possibly heavy tailed errors. Robustness to heavy tails is ensured by negligibly trimming the squared error according to extreme values of the error and regressors. Tail-trimming ensures asymptotic normality and superp -convergence with a rate comparable to the highest achieved amongst M-estimators for stationary data. Moreov...
متن کامل