Iterative constrained penalized likelihood estimation of parameters for CDMA

Khan, Ejaz; Slock, Dirk T M
Asilomar 2002, 36th IEEE Annual Asilomar conference on signals, systems and computers, November 3-6, 2002, Pacific Grove, USA

We describe an iterative method for Maximum Likelihood (ML) parameter estimation corrupted by additive white Gaussian noise. In the objective function we subtract/ add Kullback-Leibler (KL) distance function or euclidean distance function to keep the old parameter set close to the new ones and can be considered as penalty term. The above augmented cost function can be maximized/ minimized over the constraint that the detected data vector lie on the sphere. We simplify this constraint function by using first order Taylor expansion at the old parameter value. The useful behavior of the proposed algorithm is verified by numerical experiments.e describe an iterative method for Maximum Likelihood (ML) parameter estimation corrupted by additive white Gaussian noise. In the objective function we subtract/ add Kullback-Leibler (KL) distance function or euclidean distance function to keep the old parameter set close to the new ones and can be considered as penalty term. The above augmented cost function can be maximized/ minimized over the constraint that the detected data vector lie on the sphere. We simplify this constraint function by using first order Taylor expansion at the old parameter value. The useful behavior of the proposed algorithm is verified by numerical experiments.


DOI
Type:
Conférence
City:
Pacific Grove
Date:
2002-11-03
Department:
Systèmes de Communication
Eurecom Ref:
1037
Copyright:
© 2002 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
See also:

PERMALINK : https://www.eurecom.fr/publication/1037