Katalog GES



Speeding up MCMC by delayed acceptance and data subsampling

1st Person: Quiroz, Matias
Additional Persons: Villani, Mattias; Kohn, Robert
Type of Publication: Paper
Language: English
Published: Sveriges Riksbank 2015
Series: Sveriges Riksbank Working Paper Series
Online: https://www.econstor.eu/bitstream/10419/129721/1/832334022.pdf
id
oai_econstor.eu_10419-129721
recordtype
econstor
institution
MPG
collection
ECONSTOR
title
Speeding up MCMC by delayed acceptance and data subsampling
spellingShingle
Speeding up MCMC by delayed acceptance and data subsampling
Quiroz, Matias
Sveriges Riksbank Working Paper Series
title_short
Speeding up MCMC by delayed acceptance and data subsampling
title_full
Speeding up MCMC by delayed acceptance and data subsampling
title_fullStr
Speeding up MCMC by delayed acceptance and data subsampling
title_full_unstemmed
Speeding up MCMC by delayed acceptance and data subsampling
title_sort
Speeding up MCMC by delayed acceptance and data subsampling
format
electronic Article
format_phy_str_mv
Paper
publisher
Sveriges Riksbank
publishDate
2015
language
English
author
Quiroz, Matias
author2
Villani, Mattias
Kohn, Robert
author2Str
Villani, Mattias
Kohn, Robert
description
We propose a generic Markov Chain Monte Carlo (MCMC) algorithm to speed up computations for datasets with many observations. A key feature of our approach is the use of the highly efficient difference estimator from the survey sampling literature to estimate the log-likelihood accurately using only a small fraction of the data. Our algorithm improves on the O(n) complexity of regular MCMC by operating over local data clusters instead of the full sample when computing the likelihood. The likelihood estimate is used in a Pseudo- marginal framework to sample from a perturbed posterior which is within O(m-1/2) of the true posterior, where m is the subsample size. The method is applied to a logistic regression model to predict firm bankruptcy for a large data set. We document a significant speed up in comparison to the standard MCMC on the full dataset.
url
https://www.econstor.eu/bitstream/10419/129721/1/832334022.pdf
series
Sveriges Riksbank Working Paper Series
seriesStr
Sveriges Riksbank Working Paper Series
Sveriges Riksbank Working Paper Series
series2
Sveriges Riksbank Working Paper Series
series2_facet
Sveriges Riksbank Working Paper Series
up_date
2019-05-24T02:51:03.825Z
_version_
1634380062283268098

Similar Items

Cannot find similar records

Library Services

Search Options

Quick links

Orientation