{
  "id": 10604,
  "url": "https://arxiv.org/abs/2607.13402v1",
  "title": "Price of Fairness in Bandits: A Tight Minimax Characterization",
  "summary": "In bandit problems, standard regret-minimizing algorithms treat exploration as an amortized cost, which can expose early participants to unfair ex-ante losses in settings such as clinical trials. Recent work addresses this by evaluating the sequence of per-round expected rewards through the generalized $p$-mean, interpolating between utilitarian welfare ($p=1$), Nash welfare ($p\\to0$), and Rawlsian fairness ($p\\to-\\infty$). Although tight guarantees are known for $p\\ge0$, the strictly fair regim",
  "authors": "Dhruv Sarkar, Soumyadeep Dutta, Sayak Ray Chowdhury",
  "category": "research",
  "topics": "bias-fairness,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-15T02:58:57.000Z",
  "fetched_at": "2026-07-16T05:10:56.605Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/10604",
  "original_url": "https://arxiv.org/abs/2607.13402v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}