Implementation of Sequential Importance Sampling in GPGPU

Author

Hayashi, K. ; Saito, M.M. ; Yoshida, R. ; Higuchi, T.

Author_Institution

Inst. of Stat. Math., Tokyo, Japan

fYear

2010

fDate

26-29 July 2010

Firstpage

1

Lastpage

6

Abstract

The estimation of many unknown parameters is carried out using a simplified Sequential Importance Sampling (SIS) algorithm which is implemented in a graphic processing unit (GPU). The aim of the present work is to show technical points to bring out the performance of GPU. Using the implemented code, two numerical experiments are demonstrated. In the first demonstration, it is shown that a parameter estimation involving 10⁹ Monte Carlo samples is completed within eight hours. In the second demonstration, accuracy-guaranteed evaluation of the likelihood is carried out.

Keywords

computer graphic equipment; coprocessors; general purpose computers; importance sampling; parameter estimation; GPGPU; Monte Carlo samples; graphic processing unit; numerical experiment; parameter estimation; sequential importance sampling; Biological system modeling; Computational modeling; Data models; Graphics processing unit; Instruction sets; Mathematical model; Monte Carlo methods; GPGPU programming; Monte Carlo method; parameter estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Fusion (FUSION), 2010 13th Conference on

Conference_Location

Edinburgh

Print_ISBN

978-0-9824438-1-1

Type

conf

DOI

10.1109/ICIF.2010.5712017

Filename

5712017