0 of 0       
Essec\Faculty\Model\Contribution {#2233 ▼
  #_index: "academ_contributions"
  #_id: "14317"
  #_source: array:26 [
    "id" => "14317"
    "slug" => "14317-monotonic-alpha-divergence-minimisation-for-variational-inference"
    "yearMonth" => "2023-01"
    "year" => "2023"
    "title" => "Monotonic Alpha-divergence Minimisation for Variational Inference"
    "description" => "DAUDEL, K., DOUC, R. et ROUEFF, F. (2023). Monotonic Alpha-divergence Minimisation for Variational Inference. <i>Journal of Machine Learning Research</i>, 24(62), pp. 1-76. DAUDEL, K., DOUC, R. et ROUEFF, F. (2023). Monotonic Alpha-divergence Minimisation for Variational I "
    "authors" => array:3 [
      0 => array:3 [
        "name" => "DAUDEL Kamélia"
        "bid" => "B00812202"
        "slug" => "daudel-kamelia"
      ]
      1 => array:1 [
        "name" => "DOUC Randal"
      ]
      2 => array:1 [
        "name" => "ROUEFF François"
      ]
    ]
    "ouvrage" => ""
    "keywords" => []
    "updatedAt" => "2024-10-31 13:51:19"
    "publicationUrl" => "http://jmlr.org/papers/v24/21-0249.html"
    "publicationInfo" => array:3 [
      "pages" => "1-76"
      "volume" => "24"
      "number" => "62"
    ]
    "type" => array:2 [
      "fr" => "Articles"
      "en" => "Journal articles"
    ]
    "support_type" => array:2 [
      "fr" => "Revue scientifique"
      "en" => "Scientific journal"
    ]
    "countries" => array:2 [
      "fr" => "États-Unis"
      "en" => "United States of America"
    ]
    "abstract" => array:2 [
      "fr" => """
        In this paper, we introduce a novel family of iterative algorithms which carry out α\n
        -divergence minimisation in a Variational Inference context. They do so by ensuring a systematic decrease at each step in the α\n -divergence minimisation in a Variational Inference context. They do so by ensuring a systematic dec 
        -divergence between the variational and the posterior distributions. In its most general form, the variational distribution is a mixture model and our framework allows us to simultaneously optimise the weights and components parameters of this mixture model. Our approach permits us to build on various methods previously proposed for α\n -divergence between the variational and the posterior distributions. In its most general form, the v 
        -divergence minimisation such as Gradient or Power Descent schemes and we also shed a new light on an integrated Expectation Maximization algorithm. Lastly, we provide empirical evidence that our methodology yields improved results on several multimodal target distributions and on a real data example. -divergence minimisation such as Gradient or Power Descent schemes and we also shed a new light on a 
        """
      "en" => """
        In this paper, we introduce a novel family of iterative algorithms which carry out α\n
        -divergence minimisation in a Variational Inference context. They do so by ensuring a systematic decrease at each step in the α\n -divergence minimisation in a Variational Inference context. They do so by ensuring a systematic dec 
        -divergence between the variational and the posterior distributions. In its most general form, the variational distribution is a mixture model and our framework allows us to simultaneously optimise the weights and components parameters of this mixture model. Our approach permits us to build on various methods previously proposed for α\n -divergence between the variational and the posterior distributions. In its most general form, the v 
        -divergence minimisation such as Gradient or Power Descent schemes and we also shed a new light on an integrated Expectation Maximization algorithm. Lastly, we provide empirical evidence that our methodology yields improved results on several multimodal target distributions and on a real data example. -divergence minimisation such as Gradient or Power Descent schemes and we also shed a new light on a 
        """
    ]
    "authors_fields" => array:2 [
      "fr" => "Systèmes d'Information, Data Analytics et Opérations"
      "en" => "Information Systems, Data Analytics and Operations"
    ]
    "indexedAt" => "2025-04-05T20:21:40.000Z"
    "docTitle" => "Monotonic Alpha-divergence Minimisation for Variational Inference"
    "docSurtitle" => "Articles"
    "authorNames" => "<a href="/cv/daudel-kamelia">DAUDEL Kamélia</a>, DOUC Randal, ROUEFF François"
    "docDescription" => "<span class="document-property-authors">DAUDEL Kamélia, DOUC Randal, ROUEFF François</span><br><span class="document-property-authors_fields">Systèmes d'Information, Data Analytics et Opérations</span> | <span class="document-property-year">2023</span> <span class="document-property-authors">DAUDEL Kamélia, DOUC Randal, ROUEFF François</span><br><span "
    "keywordList" => ""
    "docPreview" => "<b>Monotonic Alpha-divergence Minimisation for Variational Inference</b><br><span>2023-01 | Articles </span> <b>Monotonic Alpha-divergence Minimisation for Variational Inference</b><br><span>2023-01 | Articles "
    "docType" => "research"
    "publicationLink" => "<a href="http://jmlr.org/papers/v24/21-0249.html" target="_blank">Monotonic Alpha-divergence Minimisation for Variational Inference</a> <a href="http://jmlr.org/papers/v24/21-0249.html" target="_blank">Monotonic Alpha-divergence Minimis "
  ]
  +lang: "fr"
  +"_type": "_doc"
  +"_score": 8.534798
  +"parent": null
}