Efficient block and time-recursive estimation of sparse Volterra systems

Author

Adalbjörnsson, Stefan I. ; Glentis, George-Othon ; Jakobsson, Andreas

Author_Institution

Math. Stat., Lund Univ., Lund, Sweden

fYear

2012

fDate

5-8 Aug. 2012

Firstpage

173

Lastpage

176

Abstract

We investigate the application of non-convex penalized least squares for parameter estimation in the Volterra model. Sparsity is promoted by introducing a weighted ℓ_q penalty on the parameters and efficient batch and time recursive algorithms are devised based on the cyclic coordinate descent approach. Numerical examples illustrate the improved performance of the proposed algorithms as compared the weighted ℓ₁ norm.

Keywords

Newton-Raphson method; computational complexity; concave programming; least squares approximations; nonlinear filters; parameter estimation; recursive estimation; Newton-Raphson style algorithm; block estimation; cyclic coordinate descent approach; nonconvex penalized least squares; parameter estimation; sparse Volterra filter; sparse Volterra systems; time-recursive estimation; Charge coupled devices; Estimation; Minimization; Optimization; Polynomials; Signal processing algorithms; Vectors; Nonlinear system identification; Sparse regression; Volterra filters;

fLanguage

English

Publisher

ieee

Conference_Titel

Statistical Signal Processing Workshop (SSP), 2012 IEEE

Conference_Location

Ann Arbor, MI

ISSN

pending

Print_ISBN

978-1-4673-0182-4

Electronic_ISBN

pending

Type

conf

DOI

10.1109/SSP.2012.6319651

Filename

6319651