{
  "abstract": "Generative AI has dramatically accelerated the rate at which new treatments---from novel pharmaceuticals to online marketing campaigns---can be conceived and deployed. As a result, modern experimentation platforms often run continuously, with treatments added as they are ready and removed when they underperform. We formalize this \"Always-On\" experimental setting, in which treatments can be dynamically generated, added to, and removed from a running experiment, and study the statistical problem of deciding whether to accept or reject each treatment while controlling for the false discovery rate. We develop sequential tests that achieve time-uniform Type-I error control under arbitrary stopping times and \"predictable\" treatment schedules. Our approach builds on the testing-by-betting framework: we construct test supermartingales for testing the average treatment effect of each treatment, and show that the construction of these test supermartingales is growth-rate optimal in an almost-sure sense.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.38695",
  "author_total": 4,
  "authors": [
    {
      "name": "Ricardo J. Sandoval"
    },
    {
      "name": "David Arbour"
    },
    {
      "name": "Avi Feller"
    },
    {
      "name": "Michael I. Jordan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7w7b33hxch5z0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.38695",
  "fulltext_url": null,
  "id": "7w7b33hxch5z0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.38695",
  "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",
      "stat.ME"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7215029168",
  "pdf_url": "https://arxiv.org/pdf/2609.38695",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7w7b33hxch5z0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:58Z",
      "native_id": "2609.38695",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.38695"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "Always-On Experimentation",
  "title_text": "Always-On Experimentation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:58Z",
  "url": "https://research.draconitic.com/paper/7w7b33hxch5z0",
  "venue": "arXiv",
  "versions": []
}