{
  "abstract": "Gaussian process upper confidence bound (GP-UCB) has been widely studied, though its known regret upper bound is suboptimal. To obtain near-optimal regret upper bounds, existing studies mainly focus on non-adaptive methods, such as uncertainty sampling, whose practical effectiveness is often limited. This paper shows that, under a Gaussian noise assumption, UCB-style algorithms can achieve near-optimal regret upper bounds via data thinning, a statistical technique for creating independent datasets from a single dataset. First, we show that data thinning can yield tighter confidence intervals in the bandit setting, and that a direct extension of GP-UCB achieves a near-optimal simple regret upper bound. Furthermore, by leveraging the tighter confidence intervals and combining GP-UCB with a phased elimination algorithm, we show a near-optimal cumulative regret upper bound. Finally, we demonstrate the effectiveness of UCB-style algorithms incorporating data thinning via numerical experiments.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.28136",
  "author_total": 3,
  "authors": [
    {
      "name": "Shion Takeno"
    },
    {
      "name": "Shogo Iwazaki"
    },
    {
      "name": "Ichiro Takeuchi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2nsxv3e70b3h9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.28136",
  "fulltext_url": null,
  "id": "2nsxv3e70b3h9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.28136",
  "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": "W7223111295",
  "pdf_url": "https://arxiv.org/pdf/2610.28136",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2nsxv3e70b3h9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:13Z",
      "native_id": "2610.28136",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.28136"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Near-Optimal Regret Bounds for UCB-Style Gaussian Process Bandits via Data Thinning",
  "title_text": "Near-Optimal Regret Bounds for UCB-Style Gaussian Process Bandits via Data Thinning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:13Z",
  "url": "https://research.draconitic.com/paper/2nsxv3e70b3h9",
  "venue": "arXiv",
  "versions": []
}