{
  "abstract": "We study nonnegative submodular maximization on $n$ elements subject to a general matroid of rank $k$, when the offline algorithm is given an arbitrary controlled value oracle. Our main result is an adversarial resilience theorem for the Spiteful Greedy Swap Poisson Process (SGS-Poisson): without modifying its Poisson intensity, single-element exchange rule, or spiteful drop step, the algorithm retains limiting approximation factors $1/e$ for non-monotone objectives and $1-1/e$ for monotone objectives. More precisely, given an error bound $ξ\\ge0$, under every controlled oracle $\\widehat f$ satisfying $|\\widehat f(S)-f(S)|\\le ξ$ for every set $S$, our implementation returns a feasible set with expected value at least $(1/e-\\varepsilon)OPT-O(kξ)$ and $(1-1/e-\\varepsilon)OPT-O(kξ)$, respectively, where $OPT$ is the feasible optimum. The implementation uses a \\emph{deterministically bounded} budget of $O(nk^{2}\\varepsilon^{-2}\\log n\\log^{2}(1/\\varepsilon))$ oracle calls. As a consequence, an offline-to-online reduction yields full-bandit combinatorial multi-armed bandit (CMAB) algorithms for general matroid-constrained submodular rewards with exact limiting approximation-regret factors $1/e$ and $1-1/e$ and $\\widetilde O(n^{1/5}k^{4/5}T^{4/5})$ regret over $T$ rounds. These online guarantees allow exploration to play sets that become independent after deleting at most one element; exploitation and the benchmark remain matroid-feasible. For unit-capacity partition matroids we obtain $\\widetilde O(n^{1/5}k^{3/5}T^{4/5})$ under the same exploration relaxation. We establish a deterministic query budget by truncating the Poisson process and identify the enlarged action set needed to answer its offline queries.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.12134",
  "author_total": 1,
  "authors": [
    {
      "name": "Vaneet Aggarwal"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cy7z4qtmg11cz.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.12134",
  "fulltext_url": null,
  "id": "cy7z4qtmg11cz",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.12134",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.CC"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7202346048",
  "pdf_url": "https://arxiv.org/pdf/2608.12134",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cy7z4qtmg11cz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:57Z",
      "native_id": "2608.12134",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.12134"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids, and Full-Bandit Learning",
  "title_text": "Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids, and Full-Bandit Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:57Z",
  "url": "https://research.draconitic.com/paper/cy7z4qtmg11cz",
  "venue": "arXiv",
  "versions": []
}