Numerical Perfomances of Recursive Least Squares and Predictor Based Least Squares: A Comparative Study
Summary :
The numerical properties of the recursive least squares (RLS) algorithm and its fast versions have been extensively studied. However, very few investigations are reported concerning the numerical behavior of the predictor based least squares (PLS) algorithms that provide the same least squares solutions as the RLS algorithm. This paper presents a comparative study on the numerical performances of the RLS and the backward PLS (BPLS) algorithms. Theoretical analysis of three main instability sources reported in the literature, including the overrange of the conversion factor, the loss of symmetry and the loss of positive definiteness of the inverse correlation matrix, has been done under a finite-precision arithmetic. Simulation results have confirmed the validity of our analysis. The results show that three main instability sources encountered in the RLS algorithm do not exist in the BPLS algorithm. Consequently, the BPLS algorithm provides a much more stable and robust numerical performance compared with the RLS algorithm.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E80-A No.4 pp.745-752
- Publication Date
- 1997/04/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Category
- Digital Signal Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Youhua WANG, Kenji NAKAYAMA, "Numerical Perfomances of Recursive Least Squares and Predictor Based Least Squares: A Comparative Study" in IEICE TRANSACTIONS on Fundamentals,
vol. E80-A, no. 4, pp. 745-752, April 1997, doi: .
Abstract: The numerical properties of the recursive least squares (RLS) algorithm and its fast versions have been extensively studied. However, very few investigations are reported concerning the numerical behavior of the predictor based least squares (PLS) algorithms that provide the same least squares solutions as the RLS algorithm. This paper presents a comparative study on the numerical performances of the RLS and the backward PLS (BPLS) algorithms. Theoretical analysis of three main instability sources reported in the literature, including the overrange of the conversion factor, the loss of symmetry and the loss of positive definiteness of the inverse correlation matrix, has been done under a finite-precision arithmetic. Simulation results have confirmed the validity of our analysis. The results show that three main instability sources encountered in the RLS algorithm do not exist in the BPLS algorithm. Consequently, the BPLS algorithm provides a much more stable and robust numerical performance compared with the RLS algorithm.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e80-a_4_745/_p
Copy
@ARTICLE{e80-a_4_745,
author={Youhua WANG, Kenji NAKAYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Numerical Perfomances of Recursive Least Squares and Predictor Based Least Squares: A Comparative Study},
year={1997},
volume={E80-A},
number={4},
pages={745-752},
abstract={The numerical properties of the recursive least squares (RLS) algorithm and its fast versions have been extensively studied. However, very few investigations are reported concerning the numerical behavior of the predictor based least squares (PLS) algorithms that provide the same least squares solutions as the RLS algorithm. This paper presents a comparative study on the numerical performances of the RLS and the backward PLS (BPLS) algorithms. Theoretical analysis of three main instability sources reported in the literature, including the overrange of the conversion factor, the loss of symmetry and the loss of positive definiteness of the inverse correlation matrix, has been done under a finite-precision arithmetic. Simulation results have confirmed the validity of our analysis. The results show that three main instability sources encountered in the RLS algorithm do not exist in the BPLS algorithm. Consequently, the BPLS algorithm provides a much more stable and robust numerical performance compared with the RLS algorithm.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Numerical Perfomances of Recursive Least Squares and Predictor Based Least Squares: A Comparative Study
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 745
EP - 752
AU - Youhua WANG
AU - Kenji NAKAYAMA
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E80-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 1997
AB - The numerical properties of the recursive least squares (RLS) algorithm and its fast versions have been extensively studied. However, very few investigations are reported concerning the numerical behavior of the predictor based least squares (PLS) algorithms that provide the same least squares solutions as the RLS algorithm. This paper presents a comparative study on the numerical performances of the RLS and the backward PLS (BPLS) algorithms. Theoretical analysis of three main instability sources reported in the literature, including the overrange of the conversion factor, the loss of symmetry and the loss of positive definiteness of the inverse correlation matrix, has been done under a finite-precision arithmetic. Simulation results have confirmed the validity of our analysis. The results show that three main instability sources encountered in the RLS algorithm do not exist in the BPLS algorithm. Consequently, the BPLS algorithm provides a much more stable and robust numerical performance compared with the RLS algorithm.
ER -
English
