{
  "id": "1604.01348",
  "version": "v1",
  "published": "2016-04-05T17:53:59.000Z",
  "updated": "2016-04-05T17:53:59.000Z",
  "title": "Bayesian Optimization with Exponential Convergence",
  "authors": [
    "Kenji Kawaguchi",
    "Leslie Pack Kaelbling",
    "Tomás Lozano-Pérez"
  ],
  "comment": "In NIPS 2015 (Advances in Neural Information Processing Systems 2015)",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "This paper presents a Bayesian optimization method with exponential convergence without the need of auxiliary optimization and without the delta-cover sampling. Most Bayesian optimization methods require auxiliary optimization: an additional non-convex global optimization problem, which can be time-consuming and hard to implement in practice. Also, the existing Bayesian optimization method with exponential convergence requires access to the delta-cover sampling, which was considered to be impractical. Our approach eliminates both requirements and achieves an exponential convergence rate.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-04-05T17:53:59.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "additional non-convex global optimization problem",
      "auxiliary optimization",
      "exponential convergence rate",
      "existing bayesian optimization method",
      "delta-cover sampling"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2016arXiv160401348K"
    }
  }
}