Essec\Faculty\Model\Contribution {#2216
  #_index: "academ_contributions"
  #_id: "10560"
  #_source: array:26 [
    "id" => "10560"
    "slug" => "noisy-low-rank-matrix-completion-with-general-sampling-distribution"
    "yearMonth" => "2014-11"
    "year" => "2014"
    "title" => "Noisy low-rank matrix completion with general sampling distribution."
    "description" => "KLOPP, O. (2014). Noisy low-rank matrix completion with general sampling distribution. <i>Bernoulli: A Journal of Mathematical Statistics and Probability</i>, 20(1), pp. 282-303."
    "authors" => array:1 [
      0 => array:3 [
        "name" => "KLOPP Olga"
        "bid" => "B00732676"
        "slug" => "klopp-olga"
      ]
    ]
    "ouvrage" => ""
    "keywords" => []
    "updatedAt" => "2021-07-13 14:31:38"
    "publicationUrl" => "https://projecteuclid.org/download/pdfview_1/euclid.bj/1390407290"
    "publicationInfo" => array:3 [
      "pages" => "282-303"
      "volume" => "20"
      "number" => "1"
    ]
    "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" => """
        In the present paper, we consider the problem of matrix completion with noise. Unlike previous works,\n
        we consider quite general sampling distribution and we do not need to know or to estimate the variance\n
        of the noise. Two new nuclear-norm penalized estimators are proposed, one of them of “square-root” type.\n
        We analyse their performance under high-dimensional scaling and provide non-asymptotic bounds on the\n
        Frobenius norm error. Up to a logarithmic factor, these performance guarantees are minimax optimal in a\n
        number of circumstances.
        """
      "en" => """
        In the present paper, we consider the problem of matrix completion with noise. Unlike previous works,\n
        we consider quite general sampling distribution and we do not need to know or to estimate the variance\n
        of the noise. Two new nuclear-norm penalized estimators are proposed, one of them of “square-root” type.\n
        We analyse their performance under high-dimensional scaling and provide non-asymptotic bounds on the\n
        Frobenius norm error. Up to a logarithmic factor, these performance guarantees are minimax optimal in a\n
        number of circumstances.
        """
    ]
    "authors_fields" => array:2 [
      "fr" => "Systèmes d'Information, Data Analytics et Opérations"
      "en" => "Information Systems, Data Analytics and Operations"
    ]
    "indexedAt" => "2024-12-22T03:21:45.000Z"
    "docTitle" => "Noisy low-rank matrix completion with general sampling distribution."
    "docSurtitle" => "Journal articles"
    "authorNames" => "<a href="/cv/klopp-olga">KLOPP Olga</a>"
    "docDescription" => "<span class="document-property-authors">KLOPP Olga</span><br><span class="document-property-authors_fields">Information Systems, Data Analytics and Operations</span> | <span class="document-property-year">2014</span>"
    "keywordList" => ""
    "docPreview" => "<b>Noisy low-rank matrix completion with general sampling distribution.</b><br><span>2014-11 | Journal articles </span>"
    "docType" => "research"
    "publicationLink" => "<a href="https://projecteuclid.org/download/pdfview_1/euclid.bj/1390407290" target="_blank">Noisy low-rank matrix completion with general sampling distribution.</a>"
  ]
  +lang: "en"
  +"_type": "_doc"
  +"_score": 8.957939
  +"parent": null
}