Essec\Faculty\Model\Contribution {#2216 ▼
#_index: "academ_contributions"
#_id: "14316"
#_source: array:26 [
"id" => "14316"
"slug" => "14316-infinite-dimensional-gradient-based-descent-for-alpha-divergence-minimisation"
"yearMonth" => "2021-08"
"year" => "2021"
"title" => "Infinite-dimensional gradient-based descent for alpha-divergence minimisation"
"description" => "DAUDEL, K., DOUC, R. et PORTIER, F. (2021). Infinite-dimensional gradient-based descent for alpha-divergence minimisation. <i>Annals of Statistics</i>, 49(4), pp. 2250 - 2270. 
DAUDEL, K., DOUC, R. et PORTIER, F. (2021). Infinite-dimensional gradient-based descent for alpha-di "
"authors" => array:3 [
0 => array:3 [
"name" => "DAUDEL Kamélia"
"bid" => "B00812202"
"slug" => "daudel-kamelia"
]
1 => array:1 [
"name" => "DOUC Randal"
]
2 => array:1 [
"name" => "PORTIER François"
]
]
"ouvrage" => ""
"keywords" => []
"updatedAt" => "2023-09-12 15:34:27"
"publicationUrl" => "https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-4/Infinite-dimensional-gradient-based-descent-for-alpha-divergence-minimisation/10.1214/20-AOS2035.short https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-4/Infinite-dimensional-gradi "
"publicationInfo" => array:3 [
"pages" => "2250 - 2270"
"volume" => "49"
"number" => "4"
]
"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" => "We demonstrate empirically on both toy and real-world examples the benefit of using the Power Descent and going beyond the Entropic Mirror Descent framework, which fails as the dimension grows. We demonstrate empirically on both toy and real-world examples the benefit of using the Power Descen "
"en" => "We demonstrate empirically on both toy and real-world examples the benefit of using the Power Descent and going beyond the Entropic Mirror Descent framework, which fails as the dimension grows. We demonstrate empirically on both toy and real-world examples the benefit of using the Power Descen "
]
"authors_fields" => array:2 [
"fr" => "Systèmes d'Information, Data Analytics et Opérations"
"en" => "Information Systems, Data Analytics and Operations"
]
"indexedAt" => "2025-04-08T22:21:43.000Z"
"docTitle" => "Infinite-dimensional gradient-based descent for alpha-divergence minimisation"
"docSurtitle" => "Journal articles"
"authorNames" => "<a href="/cv/daudel-kamelia">DAUDEL Kamélia</a>, DOUC Randal, PORTIER François"
"docDescription" => "<span class="document-property-authors">DAUDEL Kamélia, DOUC Randal, PORTIER François</span><br><span class="document-property-authors_fields">Information Systems, Data Analytics and Operations</span> | <span class="document-property-year">2021</span> <span class="document-property-authors">DAUDEL Kamélia, DOUC Randal, PORTIER François</span><br><spa "
"keywordList" => ""
"docPreview" => "<b>Infinite-dimensional gradient-based descent for alpha-divergence minimisation</b><br><span>2021-08 | Journal articles </span> <b>Infinite-dimensional gradient-based descent for alpha-divergence minimisation</b><br><span>2021-0 "
"docType" => "research"
"publicationLink" => "<a href="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-4/Infinite-dimensional-gradient-based-descent-for-alpha-divergence-minimisation/10.1214/20-AOS2035.short" target="_blank">Infinite-dimensional gradient-based descent for alpha-divergence minimisation</a> <a href="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-4/Infinite-dimensio "
]
+lang: "en"
+"_type": "_doc"
+"_score": 8.712693
+"parent": null
}
