{
  "id": "1904.07637",
  "version": "v1",
  "published": "2019-04-16T13:11:04.000Z",
  "updated": "2019-04-16T13:11:04.000Z",
  "title": "Learning a Gauge Symmetry with Neural Networks",
  "authors": [
    "Aurélien Decelle",
    "Victor Martin-Mayor",
    "Beatriz Seoane"
  ],
  "comment": "6 pages, 6 figures",
  "categories": [
    "cond-mat.dis-nn",
    "cond-mat.stat-mech",
    "cs.LG"
  ],
  "abstract": "We explore the capacity of neural networks to detect a symmetry with complex local and non-local patterns: the gauge symmetry $Z_2$. This symmetry is present in physical problems from topological transitions to QCD, and controls the computational hardness of instances of spin-glasses. Here, we show how to design a neural network, and a dataset, able to learn this symmetry and to find compressed latent representations of the gauge orbits. Our method pays special attention to system-wrapping loops, the so-called Polyakov loops, known to be particularly relevant for computational complexity.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-04-16T13:11:04.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "neural network",
      "gauge symmetry",
      "method pays special attention",
      "computational hardness",
      "gauge orbits"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 6,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}