{
  "id": "2305.00438",
  "version": "v1",
  "published": "2023-04-30T09:41:04.000Z",
  "updated": "2023-04-30T09:41:04.000Z",
  "title": "META-SMGO-$Δ$: similarity as a prior in black-box optimization",
  "authors": [
    "Riccardo Busetto",
    "Valentina Breschi",
    "Simone Formentin"
  ],
  "categories": [
    "math.OC",
    "cs.LG",
    "cs.SY",
    "eess.SY"
  ],
  "abstract": "When solving global optimization problems in practice, one often ends up repeatedly solving problems that are similar to each others. By providing a rigorous definition of similarity, in this work we propose to incorporate the META-learning rationale into SMGO-$\\Delta$, a global optimization approach recently proposed in the literature, to exploit priors obtained from similar past experience to efficiently solve new (similar) problems. Through a benchmark numerical example we show the practical benefits of our META-extension of the baseline algorithm, while providing theoretical bounds on its performance.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-04-30T09:41:04.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "black-box optimization",
      "similarity",
      "global optimization approach",
      "solving global optimization problems",
      "similar past experience"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}