{
  "abstract": "Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. Real-world deployments require handling streaming data, changing expert availability, shifting expert reliability, and feedback observed only for the selected action. We introduce an online multiclass L2D algorithm that combines queried-action bandit feedback with a dynamically varying pool of experts. Let $N=n+n_e$, let $B$ bound the Frobenius norm of the linear score matrix, and let $ρ$ bound the augmented input norm. Assuming linear calibration and zero surrogate minimizability gap for the projected comparator class, our method achieves expected true-deferral regret $O((BN^{3/2}ρ+1)T^{2/3})$, improving to $O(BN^{3/2}ρ\\sqrt T+B^2N^3ρ^2)$ under a concentrated-score condition. The analysis combines an online $\\mathcal H$-consistency transfer bound with projected online convex optimization. Experiments on synthetic and real-world datasets demonstrate selective routing under varying expert availability and reliability.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.12340",
  "author_total": 6,
  "authors": [
    {
      "name": "Dang Hoang Duy"
    },
    {
      "name": "Yannis Montreuil"
    },
    {
      "name": "Maxime Meyer"
    },
    {
      "name": "Axel Carlier"
    },
    {
      "name": "Lai Xing Ng"
    },
    {
      "name": "Wei Tsang Ooi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cs3wtfzftrz47.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.12340",
  "fulltext_url": null,
  "id": "cs3wtfzftrz47",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.12340",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7161049163",
  "pdf_url": "https://arxiv.org/pdf/2605.12340",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cs3wtfzftrz47.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:34Z",
      "native_id": "2605.12340",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.12340"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Online Learning-to-Defer with Varying Experts",
  "title_text": "Online Learning-to-Defer with Varying Experts",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:34Z",
  "url": "https://research.draconitic.com/paper/cs3wtfzftrz47",
  "venue": "arXiv",
  "versions": []
}