{
  "id": "1901.10682",
  "version": "v1",
  "published": "2019-01-30T05:59:17.000Z",
  "updated": "2019-01-30T05:59:17.000Z",
  "title": "On the Convergence of (Stochastic) Gradient Descent with Extrapolation for Non-Convex Optimization",
  "authors": [
    "Yi Xu",
    "Zhuoning Yuan",
    "Sen Yang",
    "Rong Jin",
    "Tianbao Yang"
  ],
  "categories": [
    "math.OC"
  ],
  "abstract": "Extrapolation is very popular in convex optimization, and even for non-convex optimizaion, several recent works have empirically shown its success in many machine learning tasks. However, it has not been analyzed for non-convex optimization and there still remains a gap between the theory and the practice. In this paper, we analyze gradient descent with extrapolation for non-convex optimization both in deterministic and stochastic settings. To the best of our knowledge, this is the first attempt to analyze GD with extrapolation both for non-convex deterministic and stochastic optimization.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-01-30T05:59:17.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "non-convex optimization",
      "extrapolation",
      "convergence",
      "analyze gradient descent",
      "analyze gd"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}