{
  "id": "2406.10775",
  "version": "v1",
  "published": "2024-06-16T01:33:22.000Z",
  "updated": "2024-06-16T01:33:22.000Z",
  "title": "A Rate-Distortion View of Uncertainty Quantification",
  "authors": [
    "Ifigeneia Apostolopoulou",
    "Benjamin Eysenbach",
    "Frank Nielsen",
    "Artur Dubrawski"
  ],
  "journal": "International Conference on Machine Learning, 2024",
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "abstract": "While powerful probabilistic models such as Gaussian Processes naturally have this property, deep neural networks often lack it. In this paper, we introduce Distance Aware Bottleneck (DAB), i.e., a new method for enriching deep neural networks with this property. Building on prior information bottleneck approaches, our method learns a codebook that stores a compressed representation of all inputs seen during training. The distance of a new example from this codebook can serve as an uncertainty estimate for the example. The resulting model is simple to train and provides deterministic uncertainty estimates by a single forward pass. Finally, our method achieves better out-of-distribution (OOD) detection and misclassification prediction than prior methods, including expensive ensemble methods, deep kernel Gaussian Processes, and approaches based on the standard information bottleneck.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-06-16T01:33:22.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "uncertainty quantification",
      "rate-distortion view",
      "deep neural networks",
      "method achieves better out-of-distribution",
      "deep kernel gaussian processes"
    ],
    "tags": [
      "journal article"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}