{
  "id": "2012.04580",
  "version": "v1",
  "published": "2020-12-08T17:26:10.000Z",
  "updated": "2020-12-08T17:26:10.000Z",
  "title": "Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods",
  "authors": [
    "James Jordon",
    "Alan Wilson",
    "Mihaela van der Schaar"
  ],
  "categories": [
    "cs.LG",
    "cs.CY"
  ],
  "abstract": "Many ground-breaking advancements in machine learning can be attributed to the availability of a large volume of rich data. Unfortunately, many large-scale datasets are highly sensitive, such as healthcare data, and are not widely available to the machine learning community. Generating synthetic data with privacy guarantees provides one such solution, allowing meaningful research to be carried out \"at scale\" - by allowing the entirety of the machine learning community to potentially accelerate progress within a given field. In this article, we provide a high-level view of synthetic data: what it means, how we might evaluate it and how we might use it.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-12-08T17:26:10.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "machine learning methods",
      "data floodgates",
      "directed development",
      "enable faster",
      "machine learning community"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}