{
  "id": "2010.13064",
  "version": "v1",
  "published": "2020-10-25T08:20:38.000Z",
  "updated": "2020-10-25T08:20:38.000Z",
  "title": "Further Analysis of Outlier Detection with Deep Generative Models",
  "authors": [
    "Ziyu Wang",
    "Bin Dai",
    "David Wipf",
    "Jun Zhu"
  ],
  "comment": "NeurIPS 2020",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling. In this work, we present a possible explanation for this phenomenon, starting from the observation that a model's typical set and high-density region may not conincide. From this vantage point we propose a novel outlier test, the empirical success of which suggests that the failure of existing likelihood-based outlier tests does not necessarily imply that the corresponding generative model is uncalibrated. We also conduct additional experiments to help disentangle the impact of low-level texture versus high-level semantics in differentiating outliers. In aggregate, these results suggest that modifications to the standard evaluation practices and benchmarks commonly applied in the literature are needed.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-10-25T08:20:38.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep generative models",
      "conduct additional experiments",
      "outlier detection applications",
      "novel outlier test",
      "standard evaluation practices"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}