Essec\Faculty\Model\Contribution {#2233 ▼
#_index: "academ_contributions"
#_id: "13891"
#_source: array:26 [
"id" => "13891"
"slug" => "13891-a-generalization-bound-for-online-variational-inference"
"yearMonth" => "2019-11"
"year" => "2019"
"title" => "A Generalization Bound for Online Variational Inference"
"description" => "CHERIEF-ABDELLATIF, B.E., ALQUIER, P. et KHAN, M.E. (2019). A Generalization Bound for Online Variational Inference. Dans: <i>11th Asian Conference on Machine Learning (ACML'19)</i>. Proceedings of Machine Learning Research. 
CHERIEF-ABDELLATIF, B.E., ALQUIER, P. et KHAN, M.E. (2019). A Generalization Bound for Online Variat "
"authors" => array:3 [
0 => array:2 [
"name" => "CHERIEF-ABDELLATIF Badr-Eddine"
"bid" => "B00810114"
]
1 => array:3 [
"name" => "ALQUIER Pierre"
"bid" => "B00809923"
"slug" => "alquier-pierre"
]
2 => array:1 [
"name" => "KHAN Mohammad Emtiyaz"
]
]
"ouvrage" => "11th Asian Conference on Machine Learning (ACML'19)"
"keywords" => []
"updatedAt" => "2024-10-31 13:51:19"
"publicationUrl" => "http://proceedings.mlr.press/v101/cherief-abdellatif19a.html"
"publicationInfo" => array:3 [
"pages" => null
"volume" => null
"number" => null
]
"type" => array:2 [
"fr" => "Actes d'une conférence"
"en" => "Conference Proceedings"
]
"support_type" => array:2 [
"fr" => "Editeur"
"en" => "Publisher"
]
"countries" => array:2 [
"fr" => "Royaume-Uni"
"en" => "United Kingdom"
]
"abstract" => array:2 [
"fr" => "Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even with model mismatch and adversaries. Unfortunately, exact Bayesian inference is rarely feasible in practice and approximation methods are usually employed, but do such methods preserve the generalization properties of Bayesian inference? In this paper, we show that this is indeed the case for some variational inference (VI) algorithms. We consider a few existing online, tempered VI algorithms, as well as a new algorithm, and derive their generalization bounds. Our theoretical result relies on the convexity of the variational objective, but we argue that the result should hold more generally and present empirical evidence in support of this. Our work in this paper presents theoretical justifications in favor of online algorithms relying on approximate Bayesian methods. Bayesian inference provides an attractive online-learning framework to analyze sequential data, and "
"en" => "Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even with model mismatch and adversaries. Unfortunately, exact Bayesian inference is rarely feasible in practice and approximation methods are usually employed, but do such methods preserve the generalization properties of Bayesian inference? In this paper, we show that this is indeed the case for some variational inference (VI) algorithms. We consider a few existing online, tempered VI algorithms, as well as a new algorithm, and derive their generalization bounds. Our theoretical result relies on the convexity of the variational objective, but we argue that the result should hold more generally and present empirical evidence in support of this. Our work in this paper presents theoretical justifications in favor of online algorithms relying on approximate Bayesian methods. Bayesian inference provides an attractive online-learning framework to analyze sequential data, and "
]
"authors_fields" => array:2 [
"fr" => "Systèmes d'Information, Data Analytics et Opérations"
"en" => "Information Systems, Data Analytics and Operations"
]
"indexedAt" => "2025-04-02T11:21:48.000Z"
"docTitle" => "A Generalization Bound for Online Variational Inference"
"docSurtitle" => "Actes d'une conférence"
"authorNames" => "CHERIEF-ABDELLATIF Badr-Eddine, <a href="/cv/alquier-pierre">ALQUIER Pierre</a>, KHAN Mohammad Emtiyaz CHERIEF-ABDELLATIF Badr-Eddine, <a href="/cv/alquier-pierre">ALQUIER Pierre</a>, KHAN Mohammad Emtiy "
"docDescription" => "<span class="document-property-authors">CHERIEF-ABDELLATIF Badr-Eddine, ALQUIER Pierre, KHAN Mohammad Emtiyaz</span><br><span class="document-property-authors_fields">Systèmes d'Information, Data Analytics et Opérations</span> | <span class="document-property-year">2019</span> <span class="document-property-authors">CHERIEF-ABDELLATIF Badr-Eddine, ALQUIER Pierre, KHAN Mohamma "
"keywordList" => ""
"docPreview" => "<b>A Generalization Bound for Online Variational Inference</b><br><span>2019-11 | Actes d'une conférence </span> <b>A Generalization Bound for Online Variational Inference</b><br><span>2019-11 | Actes d'une confér "
"docType" => "research"
"publicationLink" => "<a href="http://proceedings.mlr.press/v101/cherief-abdellatif19a.html" target="_blank">A Generalization Bound for Online Variational Inference</a> <a href="http://proceedings.mlr.press/v101/cherief-abdellatif19a.html" target="_blank">A Generalizat "
]
+lang: "fr"
+"_type": "_doc"
+"_score": 8.771896
+"parent": null
}
