Essec\Faculty\Model\Contribution {#2233 ▼
#_index: "academ_contributions"
#_id: "13879"
#_source: array:26 [
"id" => "13879"
"slug" => "13879-meta-strategy-for-learning-tuning-parameters-with-guarantees"
"yearMonth" => "2021-09"
"year" => "2021"
"title" => "Meta-Strategy for Learning Tuning Parameters with Guarantees"
"description" => "MEUNIER, D. et ALQUIER, P. (2021). Meta-Strategy for Learning Tuning Parameters with Guarantees. <i>Entropy</i>, 23(10). 
MEUNIER, D. et ALQUIER, P. (2021). Meta-Strategy for Learning Tuning Parameters with Guarantees. <i> "
"authors" => array:2 [
0 => array:3 [
"name" => "ALQUIER Pierre"
"bid" => "B00809923"
"slug" => "alquier-pierre"
]
1 => array:1 [
"name" => "MEUNIER Dimitri"
]
]
"ouvrage" => ""
"keywords" => array:7 [
0 => "meta-learning"
1 => "hyperparameters"
2 => "priors"
3 => "online learning"
4 => "Bayesian inference"
5 => "online optimization"
6 => "gradient descent"
]
"updatedAt" => "2024-10-31 13:51:19"
"publicationUrl" => "https://doi.org/10.3390/e23101257"
"publicationInfo" => array:3 [
"pages" => null
"volume" => "23"
"number" => "10"
]
"type" => array:2 [
"fr" => "Articles"
"en" => "Journal articles"
]
"support_type" => array:2 [
"fr" => "Revue scientifique"
"en" => "Scientific journal"
]
"countries" => array:2 [
"fr" => "Suisse"
"en" => "Switzerland"
]
"abstract" => array:2 [
"fr" => "Online learning methods, similar to the online gradient algorithm (OGA) and exponentially weighted aggregation (EWA), often depend on tuning parameters that are difficult to set in practice. We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks. Our strategy is based on the minimization of a regret bound. It allows us to learn the initialization and the step size in OGA with guarantees. It also allows us to learn the prior or the learning rate in EWA. We provide a regret analysis of the strategy. It allows to identify settings where meta-learning indeed improves on learning each task in isolation. Online learning methods, similar to the online gradient algorithm (OGA) and exponentially weighted a "
"en" => "Online learning methods, similar to the online gradient algorithm (OGA) and exponentially weighted aggregation (EWA), often depend on tuning parameters that are difficult to set in practice. We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks. Our strategy is based on the minimization of a regret bound. It allows us to learn the initialization and the step size in OGA with guarantees. It also allows us to learn the prior or the learning rate in EWA. We provide a regret analysis of the strategy. It allows to identify settings where meta-learning indeed improves on learning each task in isolation. Online learning methods, similar to the online gradient algorithm (OGA) and exponentially weighted a "
]
"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" => "Meta-Strategy for Learning Tuning Parameters with Guarantees"
"docSurtitle" => "Articles"
"authorNames" => "<a href="/cv/alquier-pierre">ALQUIER Pierre</a>, MEUNIER Dimitri"
"docDescription" => "<span class="document-property-authors">ALQUIER Pierre, MEUNIER Dimitri</span><br><span class="document-property-authors_fields">Systèmes d'Information, Data Analytics et Opérations</span> | <span class="document-property-year">2021</span> <span class="document-property-authors">ALQUIER Pierre, MEUNIER Dimitri</span><br><span class="docum "
"keywordList" => "<a href="#">meta-learning</a>, <a href="#">hyperparameters</a>, <a href="#">priors</a>, <a href="#">online learning</a>, <a href="#">Bayesian inference</a>, <a href="#">online optimization</a>, <a href="#">gradient descent</a> <a href="#">meta-learning</a>, <a href="#">hyperparameters</a>, <a href="#">priors</a>, <a href="#"> "
"docPreview" => "<b>Meta-Strategy for Learning Tuning Parameters with Guarantees</b><br><span>2021-09 | Articles </span> <b>Meta-Strategy for Learning Tuning Parameters with Guarantees</b><br><span>2021-09 | Articles </sp "
"docType" => "research"
"publicationLink" => "<a href="https://doi.org/10.3390/e23101257" target="_blank">Meta-Strategy for Learning Tuning Parameters with Guarantees</a> <a href="https://doi.org/10.3390/e23101257" target="_blank">Meta-Strategy for Learning Tuning Parame "
]
+lang: "fr"
+"_type": "_doc"
+"_score": 8.813438
+"parent": null
}
