{
  "id": "1801.06566",
  "version": "v1",
  "published": "2018-01-19T20:31:32.000Z",
  "updated": "2018-01-19T20:31:32.000Z",
  "title": "Model Theory and Machine Learning",
  "authors": [
    "Hunter Chase",
    "James Freitag"
  ],
  "comment": "13 pages",
  "categories": [
    "math.LO"
  ],
  "abstract": "About 25 years ago, it came to light that a single combinatorial property determines both an important dividing line in model theory (NIP) and machine learning (PAC-learnability). The following years saw a fruitful exchange of ideas between PAC learning and the model theory of NIP structures. In this article, we point out a new and similar connection between model theory and machine learning, this time developing a correspondence between \\emph{stability} and learnability in various settings of \\emph{online learning.} In particular, this gives many new examples of mathematically interesting classes which are learnable in the online setting.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-01-19T20:31:32.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "03C95",
      "03C98",
      "03C45"
    ],
    "keywords": [
      "model theory",
      "machine learning",
      "single combinatorial property determines",
      "similar connection",
      "nip structures"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 13,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}