{
  "abstract": "Distributed systems often operate under uncertainty, where minimizing expected loss may overlook rare but severe events. This paper studies a distributed risk-averse convex optimization problem in which agents cooperatively minimize the average of local conditional value-at-risk (CVaR) objectives over a time-varying network. Each agent has access only to noisy evaluations of its local loss function, rather than to its CVaR objective or gradient. We therefore develop a zeroth-order algorithm that uses sampled losses to construct empirical CVaR estimates and their gradient estimates. At each iteration, agents combine neighboring decisions and perform a local update. Under convexity and Lipschitz continuity assumptions, we prove that the agents reach exact asymptotic consensus. We also establish a finite-time expected suboptimality bound for the weighted ergodic iterate. With diminishing step sizes and fixed sample sizes, the local last iterates converge almost surely to a common optimum, and their limiting expected CVaR gap is bounded in terms of the smoothing and finite-sample errors. This distributed bound matches the parameter dependence of the centralized benchmark provided in this paper. Finally, simulations on a distributed sensor network estimation problem illustrate the efficacy of the method.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.04460",
  "author_total": 4,
  "authors": [
    {
      "name": "Siyi Wang"
    },
    {
      "name": "Kun Huang"
    },
    {
      "name": "Lei Xu"
    },
    {
      "name": "Karl H. Johansson"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d668c6s6t7tgr.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.04460",
  "fulltext_url": null,
  "id": "d668c6s6t7tgr",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.04460",
  "language": null,
  "licence": "CC0-1.0",
  "licence_label": "CC0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/publicdomain/zero/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1705|Distributed Control Multi-Agent Systems"
    ]
  ],
  "openalex": "W7211888405",
  "pdf_url": "https://arxiv.org/pdf/2609.04460",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d668c6s6t7tgr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:18Z",
      "native_id": "2609.04460",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.04460"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Distributed risk-averse optimization via CVaR",
  "title_text": "Distributed risk-averse optimization via CVaR",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:18Z",
  "url": "https://research.draconitic.com/paper/d668c6s6t7tgr",
  "venue": "arXiv",
  "versions": []
}