{
  "id": "2006.06733",
  "version": "v1",
  "published": "2020-06-11T18:49:06.000Z",
  "updated": "2020-06-11T18:49:06.000Z",
  "title": "IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method",
  "authors": [
    "Yossi Arjevani",
    "Joan Bruna",
    "Bugra Can",
    "Mert Gürbüzbalaban",
    "Stefanie Jegelka",
    "Hongzhou Lin"
  ],
  "categories": [
    "math.OC",
    "cs.LG"
  ],
  "abstract": "We introduce a framework for designing primal methods under the decentralized optimization setting where local functions are smooth and strongly convex. Our approach consists of approximately solving a sequence of sub-problems induced by the accelerated augmented Lagrangian method, thereby providing a systematic way for deriving several well-known decentralized algorithms including EXTRA arXiv:1404.6264 and SSDA arXiv:1702.08704. When coupled with accelerated gradient descent, our framework yields a novel primal algorithm whose convergence rate is optimal and matched by recently derived lower bounds. We provide experimental results that demonstrate the effectiveness of the proposed algorithm on highly ill-conditioned problems.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-11T18:49:06.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "decentralized accelerated augmented lagrangian method",
      "inexact decentralized accelerated augmented lagrangian",
      "novel primal algorithm",
      "experimental results",
      "approach consists"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}