The rejection Gibbs coupler: A perfect sampling algorithm and its application to truncated multivariate Gaussian distributions

Yufei Huang; Tadesse Ghirmai; Petar M. Djurić

The rejection Gibbs coupler: A perfect sampling algorithm and its application to truncated multivariate Gaussian distributions

Yufei Huang
, Tadesse Ghirmai
, Petar M. Djurić

Electrical Engineering

Stony Brook University

Research output: Contribution to conference › Paper › peer-review

Abstract

Recently, a new Markov chain based algorithm for drawing samples from a desired distribution has been proposed. This algorithm, also known as perfect sampling algorithm, can determine exactly when a Markov chain enters the equilibrium, and hence can output exact samples. In this paper, we introduce a perfect sampling algorithm called the rejection Gibbs coupler for perfect sampling from bounded multivariate distributions. We demonstrate an application of the rejection coupler for generation of samples from truncated multivariate Gaussian distributions.

Original language	English
Pages	42-45
Number of pages	4
State	Published - 2001
Event	2001 IEEE Workshop on Statitical Signal Processing Proceedings - Singapore, Singapore Duration: Aug 6 2001 → Aug 8 2001

Conference

Conference	2001 IEEE Workshop on Statitical Signal Processing Proceedings
Country/Territory	Singapore
City	Singapore
Period	08/6/01 → 08/8/01

Cite this

@conference{b5541124d871417dbffe3083dcdd8357,

title = "The rejection Gibbs coupler: A perfect sampling algorithm and its application to truncated multivariate Gaussian distributions",

abstract = "Recently, a new Markov chain based algorithm for drawing samples from a desired distribution has been proposed. This algorithm, also known as perfect sampling algorithm, can determine exactly when a Markov chain enters the equilibrium, and hence can output exact samples. In this paper, we introduce a perfect sampling algorithm called the rejection Gibbs coupler for perfect sampling from bounded multivariate distributions. We demonstrate an application of the rejection coupler for generation of samples from truncated multivariate Gaussian distributions.",

author = "Yufei Huang and Tadesse Ghirmai and Djuri{\'c}, \{Petar M.\}",

year = "2001",

language = "English",

pages = "42--45",

note = "2001 IEEE Workshop on Statitical Signal Processing Proceedings ; Conference date: 06-08-2001 Through 08-08-2001",

}

TY - CONF

T1 - The rejection Gibbs coupler

T2 - 2001 IEEE Workshop on Statitical Signal Processing Proceedings

AU - Huang, Yufei

AU - Ghirmai, Tadesse

AU - Djurić, Petar M.

PY - 2001

Y1 - 2001

N2 - Recently, a new Markov chain based algorithm for drawing samples from a desired distribution has been proposed. This algorithm, also known as perfect sampling algorithm, can determine exactly when a Markov chain enters the equilibrium, and hence can output exact samples. In this paper, we introduce a perfect sampling algorithm called the rejection Gibbs coupler for perfect sampling from bounded multivariate distributions. We demonstrate an application of the rejection coupler for generation of samples from truncated multivariate Gaussian distributions.

AB - Recently, a new Markov chain based algorithm for drawing samples from a desired distribution has been proposed. This algorithm, also known as perfect sampling algorithm, can determine exactly when a Markov chain enters the equilibrium, and hence can output exact samples. In this paper, we introduce a perfect sampling algorithm called the rejection Gibbs coupler for perfect sampling from bounded multivariate distributions. We demonstrate an application of the rejection coupler for generation of samples from truncated multivariate Gaussian distributions.

UR - https://www.scopus.com/pages/publications/0035556202

M3 - Paper

AN - SCOPUS:0035556202

SP - 42

EP - 45

Y2 - 6 August 2001 through 8 August 2001

ER -

The rejection Gibbs coupler: A perfect sampling algorithm and its application to truncated multivariate Gaussian distributions

Abstract

Conference

Other files and links

Fingerprint

Cite this