Essec\Faculty\Model\Contribution {#2206
#_index: "academ_contributions"
#_id: "13893"
#_source: array:26 [
"id" => "13893"
"slug" => "informed-sub-sampling-mcmc-approximate-bayesian-inference-for-large-datasets"
"yearMonth" => "2019-05"
"year" => "2019"
"title" => "Informed sub-sampling MCMC: approximate Bayesian inference for large datasets"
"description" => "MAIRE, F., FRIEL, N. et ALQUIER, P. (2019). Informed sub-sampling MCMC: approximate Bayesian inference for large datasets. <i>Statistics and Computing</i>, 29(3), pp. 449-482."
"authors" => array:3 [
0 => array:3 [
"name" => "ALQUIER Pierre"
"bid" => "B00809923"
"slug" => "alquier-pierre"
]
1 => array:1 [
"name" => "MAIRE Florian"
]
2 => array:1 [
"name" => "FRIEL Nial"
]
]
"ouvrage" => ""
"keywords" => []
"updatedAt" => "2023-03-22 09:45:27"
"publicationUrl" => "https://link.springer.com/article/10.1007/s11222-018-9817-3"
"publicationInfo" => array:3 [
"pages" => "449-482"
"volume" => "29"
"number" => "3"
]
"type" => array:2 [
"fr" => "Articles"
"en" => "Journal articles"
]
"support_type" => array:2 [
"fr" => "Revue scientifique"
"en" => "Scientific journal"
]
"countries" => array:2 [
"fr" => null
"en" => null
]
"abstract" => array:2 [
"fr" => "This paper introduces a framework for speeding up Bayesian inference conducted in presence of large datasets. We design a Markov chain whose transition kernel uses an unknown fraction of fixed size of the available data that is randomly refreshed throughout the algorithm. Inspired by the Approximate Bayesian Computation literature, the subsampling process is guided by the fidelity to the observed data, as measured by summary statistics. The resulting algorithm, Informed Sub-Sampling MCMC, is a generic and flexible approach which, contrary to existing scalable methodologies, preserves the simplicity of the Metropolis–Hastings algorithm. Even though exactness is lost, i.e. the chain distribution approximates the posterior, we study and quantify theoretically this bias and show on a diverse set of examples that it yields excellent performances when the computational budget is limited. If available and cheap to compute, we show that setting the summary statistics as the maximum likelihood estimator is supported by theoretical arguments."
"en" => "This paper introduces a framework for speeding up Bayesian inference conducted in presence of large datasets. We design a Markov chain whose transition kernel uses an unknown fraction of fixed size of the available data that is randomly refreshed throughout the algorithm. Inspired by the Approximate Bayesian Computation literature, the subsampling process is guided by the fidelity to the observed data, as measured by summary statistics. The resulting algorithm, Informed Sub-Sampling MCMC, is a generic and flexible approach which, contrary to existing scalable methodologies, preserves the simplicity of the Metropolis–Hastings algorithm. Even though exactness is lost, i.e. the chain distribution approximates the posterior, we study and quantify theoretically this bias and show on a diverse set of examples that it yields excellent performances when the computational budget is limited. If available and cheap to compute, we show that setting the summary statistics as the maximum likelihood estimator is supported by theoretical arguments."
]
"authors_fields" => array:2 [
"fr" => "Systèmes d'Information, Data Analytics et Opérations"
"en" => "Information Systems, Data Analytics and Operations"
]
"indexedAt" => "2024-10-06T23:21:46.000Z"
"docTitle" => "Informed sub-sampling MCMC: approximate Bayesian inference for large datasets"
"docSurtitle" => "Articles"
"authorNames" => "<a href="/cv/alquier-pierre">ALQUIER Pierre</a>, MAIRE Florian, FRIEL Nial"
"docDescription" => "<span class="document-property-authors">ALQUIER Pierre, MAIRE Florian, FRIEL Nial</span><br><span class="document-property-authors_fields">Systèmes d'Information, Data Analytics et Opérations</span> | <span class="document-property-year">2019</span>"
"keywordList" => ""
"docPreview" => "<b>Informed sub-sampling MCMC: approximate Bayesian inference for large datasets</b><br><span>2019-05 | Articles </span>"
"docType" => "research"
"publicationLink" => "<a href="https://link.springer.com/article/10.1007/s11222-018-9817-3" target="_blank">Informed sub-sampling MCMC: approximate Bayesian inference for large datasets</a>"
]
+lang: "fr"
+"_type": "_doc"
+"_score": 8.4668255
+"parent": null
}