{
  "abstract": "Exploration in centralized serial-dictatorship matching bandits must use complete matchings, so learning one player-arm pair can impose regret on others. We study this externality under a known common priority order and Gaussian rewards with unit variance. We show that the matching-level Graves-Lai constraints reduce to finitely many pairwise exploration quotas and, at top-choice-separated instances, yield a polynomial-size marginal linear program. At these instances, the exact attainable set of expected logarithmic regret coefficients is $G(θ)\\mathcal{X}(θ)$, where $\\mathcal{X}$ is the feasible matching-allocation set and $G$ maps allocations to player regret. The usual upper-closed Graves-Lai region can be strictly larger despite having the same Pareto-minimal boundary. We further show that identical exploration quotas can induce very different regret through their scheduling. Finally, we construct estimate-solve-track policies, uniformly good on the full row-strict class, that attain every fixed positively weighted optimum without assuming optimizer uniqueness. Every Pareto-minimal point is pointwise attainable, possibly through an instance-calibrated target.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.19963",
  "author_total": 4,
  "authors": [
    {
      "name": "Lishang Xu"
    },
    {
      "name": "Guodong Ma"
    },
    {
      "name": "Pengcheng Weng"
    },
    {
      "name": "Zixuan Xia"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/46rehg0v35zmt.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.19963",
  "fulltext_url": null,
  "id": "46rehg0v35zmt",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.19963",
  "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.GT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7213608202",
  "pdf_url": "https://arxiv.org/pdf/2609.19963",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/46rehg0v35zmt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:16Z",
      "native_id": "2609.19963",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.19963"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits",
  "title_text": "Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:16Z",
  "url": "https://research.draconitic.com/paper/46rehg0v35zmt",
  "venue": "arXiv",
  "versions": []
}