{
  "abstract": "Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made for stochastic bandits and non-contextual adversarial bandits, meta-learning for adversarial linear contextual bandits (ALCBs) with random action sets remains largely unexplored. To address this problem, we propose Meta-LinEXP3, an online-within-online algorithm that constructs a predictable task-level prior from completed tasks to guide the inner LinEXP3 learner. For known context distributions, we develop a policy-centered estimator that achieves an intrinsic-dimension $\\mathcal{O}(\\sqrt{n})$ per-task regret bound. For unknown distributions, we introduce a past-only regularized moment estimator with an $\\mathcal{O}(n^{2/3})$ leading regret term and explicit finite-sample error. We further establish a direct connection between prior accuracy and transfer regret, showing that increasingly accurate priors yield sublinear transfer-dependent regret across tasks. Experiments demonstrate the effectiveness of Meta-LinEXP3, including its application to structured hyperspectral tensor sampling.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.09907",
  "author_total": 3,
  "authors": [
    {
      "name": "Hao Li"
    },
    {
      "name": "Jie Xu"
    },
    {
      "name": "Zheng Xie"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bar5j2qy6erh8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.09907",
  "fulltext_url": null,
  "id": "bar5j2qy6erh8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.09907",
  "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",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7212325924",
  "pdf_url": "https://arxiv.org/pdf/2609.09907",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bar5j2qy6erh8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:45Z",
      "native_id": "2609.09907",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.09907"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits",
  "title_text": "Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:45Z",
  "url": "https://research.draconitic.com/paper/bar5j2qy6erh8",
  "venue": "arXiv",
  "versions": []
}