Home > Research > Publications & Outputs > sgmcmc

Electronic data

  • 1710.00578v1

    Accepted author manuscript, 522 KB, PDF document

    Available under license: CC BY

Links

Text available via DOI:

View graph of relations

sgmcmc: An R Package for Stochastic Gradient Markov Chain Monte Carlo

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

sgmcmc: An R Package for Stochastic Gradient Markov Chain Monte Carlo. / Baker, Jack; Fearnhead, Paul; Fox, Emily B. et al.
In: Journal of Statistical Software, Vol. 91, No. 3, 31.10.2019, p. 1-27.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Baker J, Fearnhead P, Fox EB, Nemeth CJ. sgmcmc: An R Package for Stochastic Gradient Markov Chain Monte Carlo. Journal of Statistical Software. 2019 Oct 31;91(3):1-27. doi: 10.18637/jss.v091.i03

Author

Baker, Jack ; Fearnhead, Paul ; Fox, Emily B. et al. / sgmcmc : An R Package for Stochastic Gradient Markov Chain Monte Carlo. In: Journal of Statistical Software. 2019 ; Vol. 91, No. 3. pp. 1-27.

Bibtex

@article{325b341c0a584b7bb0b0c997073b4133,
title = "sgmcmc: An R Package for Stochastic Gradient Markov Chain Monte Carlo",
abstract = "This paper introduces the R package sgmcmc; which can be used for Bayesian inference on problems with large datasets using stochastic gradient Markov chain Monte Carlo (SGMCMC). Traditional Markov chain Monte Carlo (MCMC) methods, such as Metropolis-Hastings, are known to run prohibitively slowly as the dataset size increases. SGMCMC solves this issue by only using a subset of data at each iteration. SGMCMC requires calculating gradients of the log likelihood and log priors, which can be time consuming and error prone to perform by hand. The sgmcmc package calculates these gradients itself using automatic differentiation, making the implementation of these methods much easier. To do this, the package uses the software library TensorFlow, which has a variety of statistical distributions and mathematical operations as standard, meaning a wide class of models can be built using this framework. SGMCMC has become widely adopted in the machine learning literature, but less so in the statistics community. We believe this may be partly due to lack of software; this package aims to bridge this gap.",
keywords = "stat.CO, stat.AP, stat.ML",
author = "Jack Baker and Paul Fearnhead and Fox, {Emily B.} and Nemeth, {Christopher John}",
year = "2019",
month = oct,
day = "31",
doi = "10.18637/jss.v091.i03",
language = "English",
volume = "91",
pages = "1--27",
journal = "Journal of Statistical Software",
issn = "1548-7660",
publisher = "University of California at Los Angeles",
number = "3",

}

RIS

TY - JOUR

T1 - sgmcmc

T2 - An R Package for Stochastic Gradient Markov Chain Monte Carlo

AU - Baker, Jack

AU - Fearnhead, Paul

AU - Fox, Emily B.

AU - Nemeth, Christopher John

PY - 2019/10/31

Y1 - 2019/10/31

N2 - This paper introduces the R package sgmcmc; which can be used for Bayesian inference on problems with large datasets using stochastic gradient Markov chain Monte Carlo (SGMCMC). Traditional Markov chain Monte Carlo (MCMC) methods, such as Metropolis-Hastings, are known to run prohibitively slowly as the dataset size increases. SGMCMC solves this issue by only using a subset of data at each iteration. SGMCMC requires calculating gradients of the log likelihood and log priors, which can be time consuming and error prone to perform by hand. The sgmcmc package calculates these gradients itself using automatic differentiation, making the implementation of these methods much easier. To do this, the package uses the software library TensorFlow, which has a variety of statistical distributions and mathematical operations as standard, meaning a wide class of models can be built using this framework. SGMCMC has become widely adopted in the machine learning literature, but less so in the statistics community. We believe this may be partly due to lack of software; this package aims to bridge this gap.

AB - This paper introduces the R package sgmcmc; which can be used for Bayesian inference on problems with large datasets using stochastic gradient Markov chain Monte Carlo (SGMCMC). Traditional Markov chain Monte Carlo (MCMC) methods, such as Metropolis-Hastings, are known to run prohibitively slowly as the dataset size increases. SGMCMC solves this issue by only using a subset of data at each iteration. SGMCMC requires calculating gradients of the log likelihood and log priors, which can be time consuming and error prone to perform by hand. The sgmcmc package calculates these gradients itself using automatic differentiation, making the implementation of these methods much easier. To do this, the package uses the software library TensorFlow, which has a variety of statistical distributions and mathematical operations as standard, meaning a wide class of models can be built using this framework. SGMCMC has become widely adopted in the machine learning literature, but less so in the statistics community. We believe this may be partly due to lack of software; this package aims to bridge this gap.

KW - stat.CO

KW - stat.AP

KW - stat.ML

U2 - 10.18637/jss.v091.i03

DO - 10.18637/jss.v091.i03

M3 - Journal article

VL - 91

SP - 1

EP - 27

JO - Journal of Statistical Software

JF - Journal of Statistical Software

SN - 1548-7660

IS - 3

ER -