{
  "abstract": "Federated learning (FL) is an emerging distributed machine learning paradigm that enables local devices to jointly train a global model while keeping data decentralized and private. We propose a variance-reduction based algorithm, VRA-FedSGD, for FL in the presence of heavy-tailed gradient noise and communication noise, where these noises are prevalent in large-scale machine learning over wireless networks and Internet of Things deployments. VRA-FedSGD employs a momentum variance reduction technique together with a nonlinear mapping to mitigate heavy-tailed gradient noise, and uses a variance-reduced aggregation mechanism to suppress heavy-tailed communication noise. In the mean sense, VRA-FedSGD achieves a convergence rate of {\\small$\\mathcal{O}\\left(K^{-(p-1)/(2p-1)}\\right)$} for nonconvex objective functions, where $p$ is the tail index of heavy-tailed noise. In the almost sure sense, VRA-FedSGD achieves a convergence rate of $\\tilde{\\mathcal{O}}\\left(K^{-(1-1/(p-ε))}\\right)$ for strongly convex objective functions, where $ε$ is an arbitrarily small constant. Simulated experiments on a logistic regression problem with real-world data verify the effectiveness of VRA-FedSGD.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.22466",
  "author_total": 2,
  "authors": [
    {
      "name": "Shengchao Zhao"
    },
    {
      "name": "Yongchao Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7eyee8jxrnyks.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.22466",
  "fulltext_url": null,
  "id": "7eyee8jxrnyks",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.22466",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1702|Privacy-Preserving Technologies in Data"
    ]
  ],
  "openalex": "W7165666959",
  "pdf_url": "https://arxiv.org/pdf/2606.22466",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7eyee8jxrnyks.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:08Z",
      "native_id": "2606.22466",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.22466"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm",
  "title_text": "Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:08Z",
  "url": "https://research.draconitic.com/paper/7eyee8jxrnyks",
  "venue": "arXiv",
  "versions": []
}