{
  "id": "1902.00532",
  "version": "v1",
  "published": "2019-02-01T19:29:38.000Z",
  "updated": "2019-02-01T19:29:38.000Z",
  "title": "Hyper-parameter Tuning under a Budget Constraint",
  "authors": [
    "Zhiyun Lu",
    "Chao-Kai Chiang",
    "Fei Sha"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "We study a budgeted hyper-parameter tuning problem, where we optimize the tuning result under a hard resource constraint. We propose to solve it as a sequential decision making problem, such that we can use the partial training progress of configurations to dynamically allocate the remaining budget. Our algorithm combines a Bayesian belief model which estimates the future performance of configurations, with an action-value function which balances exploration-exploitation tradeoff, to optimize the final output. It automatically adapts the tuning behaviors to different constraints, which is useful in practice. Experiment results demonstrate superior performance over existing algorithms, including the-state-of-the-art one, on real-world tuning tasks across a range of different budgets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-02-01T19:29:38.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "budget constraint",
      "experiment results demonstrate superior performance",
      "balances exploration-exploitation tradeoff",
      "bayesian belief model",
      "sequential decision making problem"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}