DocumentCode :
3282325
Title :
Score-Function Quantization for Distributed Estimation
Author :
Venkitasubramaniam, Parvathinathan ; Tong, Lang ; Swami, Ananthram
Author_Institution :
Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY
fYear :
2006
fDate :
22-24 March 2006
Firstpage :
369
Lastpage :
374
Abstract :
We study the problem of quantization for distributed parameter estimation. We propose the design of score-function quantizers to optimize different metrics of estimation performance. Score-function quantizers are a class of quantizers known to maximize the Fisher information for a fixed value of parameter thetas. We show that for distributions that satisfy a monotonicity property, the class of score-function quantizers can be made independent of parameter thetas. We then propose a generic algorithm to obtain the optimal Score-function quantizer that can be used to maximize three different metrics; minimum Fisher information, Bayesian Fisher information and minimum asymptotic relative efficiency. Through numerical examples, we illustrate that these algorithms converge to the optimal quantizers obtained through known algorithms for maximin ARE and Bayesian Fisher information.
Keywords :
Bayes methods; minimax techniques; parameter estimation; quantisation (signal); Bayesian Fisher information; distributed parameter estimation; generic algorithm; maximin ARE; minimum Fisher information; minimum asymptotic relative efficiency; score-function quantization; Bayesian methods; Collaborative work; Design optimization; Distributed computing; Government; Inference algorithms; Laboratories; Military computing; Parameter estimation; Quantization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Sciences and Systems, 2006 40th Annual Conference on
Conference_Location :
Princeton, NJ
Print_ISBN :
1-4244-0349-9
Electronic_ISBN :
1-4244-0350-2
Type :
conf
DOI :
10.1109/CISS.2006.286494
Filename :
4067835
Link To Document :
بازگشت