Emcee: The MCMC hammer

Daniel Foreman-Mackey; David W. Hogg; Dustin Lang; Jonathan Goodman

doi:10.1086/670067

Emcee: The MCMC hammer

Daniel Foreman-Mackey, David W. Hogg, Dustin Lang, Jonathan Goodman

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

We introduce a stable, well tested Python implementation of the affine-invariant ensemble sampler for Markov chain Monte Carlo (MCMC) proposed by Goodman & Weare (2010). The code is open source and has already been used in several published projects in the astrophysics literature. The algorithm behind emcee has several advantages over traditional MCMC sampling methods and it has excellent performance as measured by the autocorrelation time (or function calls per independent sample). One major advantage of the algorithm is that it requires hand-tuning of only 1 or 2 parameters compared to ~N²for a traditional algorithm in an N-dimensional parameter space. In this document, we describe the algorithm and the details of our implementation. Exploiting the parallelism of the ensemble method, emcee permits any user to take advantage of multiple CPU cores without extra effort. The code is available online at http://dan.iel.fm/emcee under the GNU General Public License v2.

Original language	English (US)
Pages (from-to)	306-312
Number of pages	7
Journal	Publications of the Astronomical Society of the Pacific
Volume	125
Issue number	925
DOIs	https://doi.org/10.1086/670067
State	Published - Mar 1 2013

ASJC Scopus subject areas

Astronomy and Astrophysics
Space and Planetary Science

Access to Document

10.1086/670067

Cite this

@article{c6973d92d76347579770c42f76305685,

title = "Emcee: The MCMC hammer",

abstract = "We introduce a stable, well tested Python implementation of the affine-invariant ensemble sampler for Markov chain Monte Carlo (MCMC) proposed by Goodman & Weare (2010). The code is open source and has already been used in several published projects in the astrophysics literature. The algorithm behind emcee has several advantages over traditional MCMC sampling methods and it has excellent performance as measured by the autocorrelation time (or function calls per independent sample). One major advantage of the algorithm is that it requires hand-tuning of only 1 or 2 parameters compared to ~N2for a traditional algorithm in an N-dimensional parameter space. In this document, we describe the algorithm and the details of our implementation. Exploiting the parallelism of the ensemble method, emcee permits any user to take advantage of multiple CPU cores without extra effort. The code is available online at http://dan.iel.fm/emcee under the GNU General Public License v2.",

author = "Daniel Foreman-Mackey and Hogg, {David W.} and Dustin Lang and Jonathan Goodman",

year = "2013",

month = mar,

day = "1",

doi = "10.1086/670067",

language = "English (US)",

volume = "125",

pages = "306--312",

journal = "Publications of the Astronomical Society of the Pacific",

issn = "0004-6280",

publisher = "Institute of Physics Publishing",

number = "925",

}

TY - JOUR

T1 - Emcee

T2 - The MCMC hammer

AU - Foreman-Mackey, Daniel

AU - Hogg, David W.

AU - Lang, Dustin

AU - Goodman, Jonathan

PY - 2013/3/1

Y1 - 2013/3/1

N2 - We introduce a stable, well tested Python implementation of the affine-invariant ensemble sampler for Markov chain Monte Carlo (MCMC) proposed by Goodman & Weare (2010). The code is open source and has already been used in several published projects in the astrophysics literature. The algorithm behind emcee has several advantages over traditional MCMC sampling methods and it has excellent performance as measured by the autocorrelation time (or function calls per independent sample). One major advantage of the algorithm is that it requires hand-tuning of only 1 or 2 parameters compared to ~N2for a traditional algorithm in an N-dimensional parameter space. In this document, we describe the algorithm and the details of our implementation. Exploiting the parallelism of the ensemble method, emcee permits any user to take advantage of multiple CPU cores without extra effort. The code is available online at http://dan.iel.fm/emcee under the GNU General Public License v2.

AB - We introduce a stable, well tested Python implementation of the affine-invariant ensemble sampler for Markov chain Monte Carlo (MCMC) proposed by Goodman & Weare (2010). The code is open source and has already been used in several published projects in the astrophysics literature. The algorithm behind emcee has several advantages over traditional MCMC sampling methods and it has excellent performance as measured by the autocorrelation time (or function calls per independent sample). One major advantage of the algorithm is that it requires hand-tuning of only 1 or 2 parameters compared to ~N2for a traditional algorithm in an N-dimensional parameter space. In this document, we describe the algorithm and the details of our implementation. Exploiting the parallelism of the ensemble method, emcee permits any user to take advantage of multiple CPU cores without extra effort. The code is available online at http://dan.iel.fm/emcee under the GNU General Public License v2.

UR - http://www.scopus.com/inward/record.url?scp=84875838326&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875838326&partnerID=8YFLogxK

U2 - 10.1086/670067

DO - 10.1086/670067

M3 - Article

AN - SCOPUS:84875838326

SN - 0004-6280

VL - 125

SP - 306

EP - 312

JO - Publications of the Astronomical Society of the Pacific

JF - Publications of the Astronomical Society of the Pacific

IS - 925

ER -

Emcee: The MCMC hammer

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this