Title :
A statistical foundation for the use of the conjugate gradient method in deconvolution
Author :
Elias, Eric D. ; Pattipati, Krishna R.
Author_Institution :
Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT, USA
Abstract :
A number of papers have suggested the use of conjugate gradient algorithms for deconvolution applications. The algebraic properties of conjugate gradient algorithms are well known with respect to minimization and linear equation solutions. Deconvolution is a subject rich in theory pertaining to linear systems and stochastic processes. This paper presents a theoretical explanation of the conjugate gradient deconvolution method in terms of signal statistics and parallel linear filters
Keywords :
FIR filters; Wiener filters; conjugate gradient methods; deconvolution; filtering theory; identification; linear systems; signal sampling; statistics; conjugate gradient method; deconvolution; linear systems; parallel linear filters; signal statistics; statistical foundation; stochastic processes; Deconvolution; Equations; Finite impulse response filter; Gradient methods; Least squares approximation; Least squares methods; Linear systems; Signal processing; Signal processing algorithms; Statistics;
Conference_Titel :
Decision and Control, 1996., Proceedings of the 35th IEEE Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-3590-2
DOI :
10.1109/CDC.1996.573609
