{
  "id": "1902.05690",
  "version": "v1",
  "published": "2019-02-15T05:28:26.000Z",
  "updated": "2019-02-15T05:28:26.000Z",
  "title": "AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices",
  "authors": [
    "Qian Lou",
    "Lantao Liu",
    "Minje Kim",
    "Lei Jiang"
  ],
  "comment": "10 pages, 12 figures",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "In this paper, we propose a hierarchical deep reinforcement learning (DRL)-based AutoML framework, AutoQB, to automatically explore the design space of channel-level network quantization and binarization for hardware-friendly deep learning on mobile devices. Compared to prior DDPG-based quantization techniques, on the various CNN models, AutoQB automatically achieves the same inference accuracy by $\\sim79\\%$ less computing overhead, or improves the inference accuracy by $\\sim2\\%$ with the same computing cost.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-02-15T05:28:26.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "mobile devices",
      "binarization",
      "inference accuracy",
      "channel-level network quantization",
      "prior ddpg-based quantization techniques"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 10,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}