{
  "id": "1907.02163",
  "version": "v1",
  "published": "2019-07-04T00:01:34.000Z",
  "updated": "2019-07-04T00:01:34.000Z",
  "title": "A Quantum Field Theory of Representation Learning",
  "authors": [
    "Robert Bamler",
    "Stephan Mandt"
  ],
  "comment": "Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning",
  "categories": [
    "stat.ML",
    "cond-mat.stat-mech",
    "cs.LG"
  ],
  "abstract": "Continuous symmetries and their breaking play a prominent role in contemporary physics. Effective low-energy field theories around symmetry breaking states explain diverse phenomena such as superconductivity, magnetism, and the mass of nucleons. We show that such field theories can also be a useful tool in machine learning, in particular for loss functions with continuous symmetries that are spontaneously broken by random initializations. In this paper, we illuminate our earlier published work (Bamler & Mandt, 2018) on this topic more from the perspective of theoretical physics. We show that the analogies between superconductivity and symmetry breaking in temporal representation learning are rather deep, allowing us to formulate a gauge theory of `charged' embedding vectors in time series models. We show that making the loss function gauge invariant speeds up convergence in such models.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-07-04T00:01:34.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "quantum field theory",
      "representation learning",
      "loss function gauge invariant speeds",
      "symmetry breaking states explain diverse",
      "breaking states explain diverse phenomena"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}