{
  "id": "1902.02603",
  "version": "v1",
  "published": "2019-02-07T13:06:43.000Z",
  "updated": "2019-02-07T13:06:43.000Z",
  "title": "Radial and Directional Posteriors for Bayesian Neural Networks",
  "authors": [
    "Changyong Oh",
    "Kamil Adamczewski",
    "Mijung Park"
  ],
  "comment": "17 pages, 9 figures",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "We propose a new variational family for Bayesian neural networks. We decompose the variational posterior into two components, where the radial component captures the strength of each neuron in terms of its magnitude; while the directional component captures the statistical dependencies among the weight parameters. The dependencies learned via the directional density provide better modeling performance compared to the widely-used Gaussian mean-field-type variational family. In addition, the strength of input and output neurons learned via the radial density provides a structured way to compress neural networks. Indeed, experiments show that our variational family improves predictive performance and yields compressed networks simultaneously.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-02-07T13:06:43.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "bayesian neural networks",
      "directional posteriors",
      "gaussian mean-field-type variational family",
      "compress neural networks",
      "directional component captures"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 17,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}