Variance analysis for least lp-norm estimator in mixture of generalized Gaussian noise

Yuan Chen; Long-Ting Huang; Xiao Long Yang; Hing Cheung So

doi:10.1587/transfun.E100.A.1226

Variance analysis for least l_p-norm estimator in mixture of generalized Gaussian noise

Yuan Chen, Long-Ting Huang, Xiao Long Yang, Hing Cheung So

Department of Electrical Engineering

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

3 Citations (Scopus)

Abstract

Variance analysis is an important research topic to assess the quality of estimators. In this paper, we analyze the performance of the least l_p-norm estimator in the presence of mixture of generalized Gaussian (MGG) noise. In the case of known density parameters, the variance expression of the l_p-norm minimizer is first derived, for the general complexvalued signal model. Since the formula is a function of p, the optimal value of p corresponding to the minimum variance is then investigated. Simulation results show the correctness of our study and the near-optimality of the lp-norm minimizer compared with Cramér-Rao lower bound.

Original language	English
Pages (from-to)	1226-1230
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E100A
Issue number	5
DOIs	https://doi.org/10.1587/transfun.E100.A.1226
Publication status	Published - 1 May 2017

Research Keywords

Complex-valued signal
Lp-norm minimizer
Mixture of generalized Gaussian model
Variance analysis

Access Output

10.1587/transfun.E100.A.1226

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{c45fc743098b4dee8946c715f3da31e3,

title = "Variance analysis for least lp-norm estimator in mixture of generalized Gaussian noise",

abstract = "Variance analysis is an important research topic to assess the quality of estimators. In this paper, we analyze the performance of the least lp-norm estimator in the presence of mixture of generalized Gaussian (MGG) noise. In the case of known density parameters, the variance expression of the lp-norm minimizer is first derived, for the general complexvalued signal model. Since the formula is a function of p, the optimal value of p corresponding to the minimum variance is then investigated. Simulation results show the correctness of our study and the near-optimality of the lp-norm minimizer compared with Cram{\'e}r-Rao lower bound.",

keywords = "Complex-valued signal, Lp-norm minimizer, Mixture of generalized Gaussian model, Variance analysis",

author = "Yuan Chen and Long-Ting Huang and Yang, {Xiao Long} and So, {Hing Cheung}",

year = "2017",

month = may,

day = "1",

doi = "10.1587/transfun.E100.A.1226",

language = "English",

volume = "E100A",

pages = "1226--1230",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "5",

}

Variance analysis for least l_p-norm estimator in mixture of generalized Gaussian noise. / Chen, Yuan; Huang, Long-Ting; Yang, Xiao Long et al.
In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E100A, No. 5, 01.05.2017, p. 1226-1230.

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

TY - JOUR

T1 - Variance analysis for least lp-norm estimator in mixture of generalized Gaussian noise

AU - Chen, Yuan

AU - Huang, Long-Ting

AU - Yang, Xiao Long

AU - So, Hing Cheung

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Variance analysis is an important research topic to assess the quality of estimators. In this paper, we analyze the performance of the least lp-norm estimator in the presence of mixture of generalized Gaussian (MGG) noise. In the case of known density parameters, the variance expression of the lp-norm minimizer is first derived, for the general complexvalued signal model. Since the formula is a function of p, the optimal value of p corresponding to the minimum variance is then investigated. Simulation results show the correctness of our study and the near-optimality of the lp-norm minimizer compared with Cramér-Rao lower bound.

AB - Variance analysis is an important research topic to assess the quality of estimators. In this paper, we analyze the performance of the least lp-norm estimator in the presence of mixture of generalized Gaussian (MGG) noise. In the case of known density parameters, the variance expression of the lp-norm minimizer is first derived, for the general complexvalued signal model. Since the formula is a function of p, the optimal value of p corresponding to the minimum variance is then investigated. Simulation results show the correctness of our study and the near-optimality of the lp-norm minimizer compared with Cramér-Rao lower bound.

KW - Complex-valued signal

KW - Lp-norm minimizer

KW - Mixture of generalized Gaussian model

KW - Variance analysis

UR - http://www.scopus.com/inward/record.url?scp=85018980586&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85018980586&origin=recordpage

U2 - 10.1587/transfun.E100.A.1226

DO - 10.1587/transfun.E100.A.1226

M3 - RGC 21 - Publication in refereed journal

SN - 0916-8508

VL - E100A

SP - 1226

EP - 1230

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 5

ER -