{
  "id": "1805.09214",
  "version": "v1",
  "published": "2018-05-23T15:13:56.000Z",
  "updated": "2018-05-23T15:13:56.000Z",
  "title": "A Unified Framework for Training Neural Networks",
  "authors": [
    "Hadi Ghauch",
    "Hossein Shokri-Ghadikolaei",
    "Carlo Fischione",
    "Mikael Skoglund"
  ],
  "comment": "15 pages, submitted to NIPS 2018",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for training different types of DNNs, and establish its convergence for arbitrary loss, activation, and regularization functions, assumed to be smooth. We show that framework generalizes well-known first- and second-order training methods, and thus allows us to show the convergence of these methods for various DNN architectures and learning tasks, as a special case of our approach. We discuss some of its applications in training various DNN architectures (e.g., feed-forward, convolutional, linear networks), to regression and classification tasks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-05-23T15:13:56.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "training neural networks",
      "unified framework",
      "dnn architectures",
      "deep neural networks",
      "framework generalizes well-known"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 15,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}