{
  "id": "1401.6276",
  "version": "v1",
  "published": "2014-01-24T07:50:28.000Z",
  "updated": "2014-01-24T07:50:28.000Z",
  "title": "The EM algorithm and the Laplace Approximation",
  "authors": [
    "Niko Brümmer"
  ],
  "categories": [
    "stat.ML"
  ],
  "abstract": "The Laplace approximation calls for the computation of second derivatives at the likelihood maximum. When the maximum is found by the EM-algorithm, there is a convenient way to compute these derivatives. The likelihood gradient can be obtained from the EM-auxiliary, while the Hessian can be obtained from this gradient with the Pearlmutter trick.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2014-01-24T07:50:28.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "em algorithm",
      "laplace approximation calls",
      "pearlmutter trick",
      "likelihood gradient",
      "second derivatives"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2014arXiv1401.6276B"
    }
  }
}