{
  "id": "1602.04847",
  "version": "v1",
  "published": "2016-02-15T21:35:58.000Z",
  "updated": "2016-02-15T21:35:58.000Z",
  "title": "Black-box optimization with a politician",
  "authors": [
    "Sébastien Bubeck",
    "Yin-Tat Lee"
  ],
  "comment": "19 pages",
  "categories": [
    "math.OC",
    "cs.DS",
    "cs.LG",
    "cs.NA"
  ],
  "abstract": "We propose a new framework for black-box convex optimization which is well-suited for situations where gradient computations are expensive. We derive a new method for this framework which leverages several concepts from convex optimization, from standard first-order methods (e.g. gradient descent or quasi-Newton methods) to analytical centers (i.e. minimizers of self-concordant barriers). We demonstrate empirically that our new technique compares favorably with state of the art algorithms (such as BFGS).",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-02-15T21:35:58.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "black-box optimization",
      "politician",
      "black-box convex optimization",
      "standard first-order methods",
      "art algorithms"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 19,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2016arXiv160204847B"
    }
  }
}