{
  "id": "1709.01716",
  "version": "v1",
  "published": "2017-09-06T08:32:50.000Z",
  "updated": "2017-09-06T08:32:50.000Z",
  "title": "Optimal Sub-sampling with Influence Functions",
  "authors": [
    "Daniel Ting",
    "Eric Brochu"
  ],
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "Sub-sampling is a common and often effective method to deal with the computational challenges of large datasets. However, for most statistical models, there is no well-motivated approach for drawing a non-uniform subsample. We show that the concept of an asymptotically linear estimator and the associated influence function leads to optimal sampling procedures for a wide class of popular models. Furthermore, for linear regression models which have well-studied procedures for non-uniform sub-sampling, we show our optimal influence function based method outperforms previous approaches. We empirically show the improved performance of our method on real datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-09-06T08:32:50.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "optimal sub-sampling",
      "optimal influence function",
      "linear regression models",
      "real datasets",
      "large datasets"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}