{
  "abstract": "We study decentralized stochastic smooth convex optimization, where $M$ workers minimize an average objective using local stochastic gradients and neighbor-only communication over a fixed gossip network. A central question in this setting is to determine the largest number of workers that can be used under a total budget of $N$ gradient samples while still preserving the centralized $O(1/\\sqrt N)$ statistical rate. We introduce an accelerated decentralized method that preserves this rate for up to $\\smash{M\\lesssim \\sqrtρ\\,N^{3/4}}$ workers, where $ρ$ is the spectral gap of the gossip network, improving the best prior maximal scaling of $\\smash{M\\lesssim ρ\\sqrt N}$. The method is based on a one-step-delayed stochastic acceleration scheme that enables workers to interleave minibatching with accelerated gossip while controlling residual disagreement, and its guarantee depends only logarithmically on the optimum-local heterogeneity. We also establish a matching lower bound for linear-span decentralized first-order methods, showing that the method is optimal up to logarithmic factors.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.04757",
  "author_total": 3,
  "authors": [
    {
      "name": "Nitai Kluger"
    },
    {
      "name": "Amit Attia"
    },
    {
      "name": "Tomer Koren"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d40ct6dnpy9hw.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.04757",
  "fulltext_url": null,
  "id": "d40ct6dnpy9hw",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.04757",
  "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|Stochastic Gradient Optimization Techniques"
    ]
  ],
  "openalex": "W7163560971",
  "pdf_url": "https://arxiv.org/pdf/2606.04757",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d40ct6dnpy9hw.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:34Z",
      "native_id": "2606.04757",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.04757"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Near-Optimal Decentralized Stochastic Convex Optimization over Networks",
  "title_text": "Near-Optimal Decentralized Stochastic Convex Optimization over Networks",
  "type": "preprint",
  "updated_at": "2026-11-07T18:20:21Z",
  "url": "https://research.draconitic.com/paper/d40ct6dnpy9hw",
  "venue": "arXiv",
  "versions": []
}