{
  "id": "2007.04617",
  "version": "v1",
  "published": "2020-07-09T08:03:49.000Z",
  "updated": "2020-07-09T08:03:49.000Z",
  "title": "Stochastic gradient descent for linear least squares problems with partially observed data",
  "authors": [
    "Kui Du",
    "Xiao-Hui Sun"
  ],
  "comment": "13 pages, 3 figures",
  "categories": [
    "math.NA",
    "cs.NA"
  ],
  "abstract": "We propose a novel stochastic gradient descent method for solving linear least squares problems with partially observed data. Our method uses submatrices indexed by a randomly selected pair of row and column index sets to update the iterate at each step. Theoretical convergence guarantees in the mean square sense are provided. Numerical experiments are reported to demonstrate the theoretical findings.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-07-09T08:03:49.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "squares problems",
      "novel stochastic gradient descent method",
      "column index sets",
      "mean square sense",
      "theoretical convergence guarantees"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 13,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}