{
  "id": "2001.05537",
  "version": "v1",
  "published": "2020-01-15T20:05:41.000Z",
  "updated": "2020-01-15T20:05:41.000Z",
  "title": "Accelerated Dual-Averaging Primal-Dual Method for Composite Convex Minimization",
  "authors": [
    "Conghui Tan",
    "Yuqiu Qian",
    "Shiqian Ma",
    "Tong Zhang"
  ],
  "journal": "Optimization Methods and Software 2020",
  "doi": "10.1080/10556788.2020.1713779",
  "categories": [
    "math.OC",
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e.g., sparsity) efficiently. In this paper, we propose a novel accelerated dual-averaging primal-dual algorithm for minimizing a composite convex function. We also derive a stochastic version of the proposed method which solves empirical risk minimization, and its advantages on handling sparse data are demonstrated both theoretically and empirically.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-01-15T20:05:41.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "accelerated dual-averaging primal-dual method",
      "composite convex minimization",
      "dual averaging-type methods",
      "industrial machine learning applications",
      "composite convex function"
    ],
    "tags": [
      "journal article"
    ],
    "publication": {
      "publisher": "Taylor-Francis"
    },
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}