{
  "abstract": "Conventional treatment policies map patient covariates to a single recommended intervention in order to maximize expected clinical outcomes. However, when multiple treatments yield statistically indistinguishable outcomes or when treatment has no effect, recommending a single intervention may result in somewhat arbitrary interventions, undermining clinical adoption and trust. To address this, we propose a set-valued policy learning paradigm. By outputting sets of valuable treatments whose cardinality reflects the recommendation’s ambiguity, our approach better supports clinical decision-making. Evaluating a set-valued policy proves subtle due to the range of possible downstream decisions. To do so, we define the set-policy value using a choice function to model clinical decision-making, and we develop doubly robust estimators thereof. Despite its practical importance, set-valued policy learning for categorical treatments remains largely unexplored. In this context, we introduce two complementary approaches: the Greatest Lower Bound method, which extends the learning-to-defer framework to multiple treatments, and conformal set-valued policy learning, which bridges the gap between unobserved ground-truth optimal treatments and estimated optimal treatment rules. Through experiments on synthetic data and real-world applications to trauma care and in-vitro fertilization (IVF), we demonstrate that our methods produce robust and actionable policies that naturally incorporate clinical considerations while effectively balancing performance and reliability.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.19830",
  "author_total": 6,
  "authors": [
    {
      "name": "Laura Fuentes-Vicente"
    },
    {
      "name": "Mathieu Even"
    },
    {
      "name": "Gaëlle Dormion"
    },
    {
      "name": "Antoine Chambaz"
    },
    {
      "name": "Uri Shalit"
    },
    {
      "name": "Julie Josse"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fgtnwj4a4rb77.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.19830",
  "fulltext_url": null,
  "id": "fgtnwj4a4rb77",
  "issns": [],
  "landing_url": "https://hal.science/hal-05673977v2",
  "language": "en",
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.ST"
    ],
    [
      "arxiv",
      "stat.TH"
    ],
    [
      "hal",
      "0.math"
    ],
    [
      "hal",
      "1.math.math-st"
    ],
    [
      "openalex",
      "2613|Advanced Causal Inference Techniques"
    ]
  ],
  "openalex": "W7161752547",
  "pdf_url": "https://hal.science/hal-05673977/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fgtnwj4a4rb77.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:54Z",
      "native_id": "hal-05673977",
      "source": "hal",
      "url": "https://hal.science/hal-05673977v2"
    },
    {
      "first_seen": "2026-10-30T12:27:42Z",
      "native_id": "2605.19830",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.19830"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.ST",
      "subfield": "statistics"
    }
  ],
  "title": "Set-Valued Policy Learning",
  "title_text": "Set-Valued Policy Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:48Z",
  "url": "https://research.draconitic.com/paper/fgtnwj4a4rb77",
  "venue": "HAL",
  "versions": []
}