Essec\Faculty\Model\Contribution {#2216
  #_index: "academ_contributions"
  #_id: "13980"
  #_source: array:26 [
    "id" => "13980"
    "slug" => "universal-robust-regression-via-maximum-mean-discrepancy"
    "yearMonth" => "2024-02"
    "year" => "2024"
    "title" => "Universal Robust Regression via Maximum Mean Discrepancy"
    "description" => "ALQUIER, P. et GERBER, M. (2024). Universal Robust Regression via Maximum Mean Discrepancy. <i>Biometrika</i>, 111(1), pp. 71-92."
    "authors" => array:2 [
      0 => array:3 [
        "name" => "ALQUIER Pierre"
        "bid" => "B00809923"
        "slug" => "alquier-pierre"
      ]
      1 => array:1 [
        "name" => "GERBER Mathieu"
      ]
    ]
    "ouvrage" => ""
    "keywords" => array:3 [
      0 => "Maximum mean discrepancy"
      1 => "Minimum distance estimator"
      2 => "Robust regression"
    ]
    "updatedAt" => "2024-10-31 13:51:19"
    "publicationUrl" => "https://doi.org/10.1093/biomet/asad031"
    "publicationInfo" => array:3 [
      "pages" => "71-92"
      "volume" => "111"
      "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" => "Many modern datasets are collected automatically and are thus easily contaminated by outliers. This has led to a renewed interest in robust estimation, including new notions of robustness such as robustness to adversarial contamination of the data. However, most robust estimation methods are designed for a specific model. Notably, many methods were proposed recently to obtain robust estimators in linear models, or generalized linear models, and a few were developed for very specific settings, for example beta regression or sample selection models. In this paper we develop a new approach for robust estimation in arbitrary regression models, based on maximum mean discrepancy minimization. We build two estimators which are both proven to be robust to Huber-type contamination. We obtain a non-asymptotic error bound for them and show that it is also robust to adversarial contamination, but this estimator is computationally more expensive to use in practice than the other one. As a by-product of our theoretical analysis of the proposed estimators we derive new results on kernel conditional mean embedding of distributions which are of independent interest."
      "en" => "Many modern datasets are collected automatically and are thus easily contaminated by outliers. This has led to a renewed interest in robust estimation, including new notions of robustness such as robustness to adversarial contamination of the data. However, most robust estimation methods are designed for a specific model. Notably, many methods were proposed recently to obtain robust estimators in linear models, or generalized linear models, and a few were developed for very specific settings, for example beta regression or sample selection models. In this paper we develop a new approach for robust estimation in arbitrary regression models, based on maximum mean discrepancy minimization. We build two estimators which are both proven to be robust to Huber-type contamination. We obtain a non-asymptotic error bound for them and show that it is also robust to adversarial contamination, but this estimator is computationally more expensive to use in practice than the other one. As a by-product of our theoretical analysis of the proposed estimators we derive new results on kernel conditional mean embedding of distributions which are of independent interest."
    ]
    "authors_fields" => array:2 [
      "fr" => "Systèmes d'Information, Data Analytics et Opérations"
      "en" => "Information Systems, Data Analytics and Operations"
    ]
    "indexedAt" => "2024-12-03T16:21:42.000Z"
    "docTitle" => "Universal Robust Regression via Maximum Mean Discrepancy"
    "docSurtitle" => "Journal articles"
    "authorNames" => "<a href="/cv/alquier-pierre">ALQUIER Pierre</a>, GERBER Mathieu"
    "docDescription" => "<span class="document-property-authors">ALQUIER Pierre, GERBER Mathieu</span><br><span class="document-property-authors_fields">Information Systems, Data Analytics and Operations</span> | <span class="document-property-year">2024</span>"
    "keywordList" => "<a href="#">Maximum mean discrepancy</a>, <a href="#">Minimum distance estimator</a>, <a href="#">Robust regression</a>"
    "docPreview" => "<b>Universal Robust Regression via Maximum Mean Discrepancy</b><br><span>2024-02 | Journal articles </span>"
    "docType" => "research"
    "publicationLink" => "<a href="https://doi.org/10.1093/biomet/asad031" target="_blank">Universal Robust Regression via Maximum Mean Discrepancy</a>"
  ]
  +lang: "en"
  +"_type": "_doc"
  +"_score": 8.758475
  +"parent": null
}