{
  "abstract": "Learning an individualized treatment rule (ITR) with many treatments requires estimating treatment-specific effects from limited observations per arm. Treatments with similar conditional responses can share information, but linear contrast models may miss nonlinear heterogeneity. We propose nonlinear supervised clustering fusion (NSCF), a neural Q-learning framework with a shared nonlinear covariate representation and low-dimensional treatment embeddings. Pairwise fusion groups treatments with similar learned contrasts, yielding an ITR and an interpretable partition. An alternating algorithm combines neural training, embedding fusion, validation-based partition selection, and unpenalized grouped refitting. NSCF lowers regret relative to a strong neural reference in nonlinear exact-sharing simulations; perturbations characterize the limits of hard sharing. In a melanoma xenograft application, NSCF improves average policy value over the neural reference. These results support nonlinear representation learning with supervised treatment fusion when treatment effects exhibit shared structure.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.19104",
  "author_total": 4,
  "authors": [
    {
      "name": "Daixi Huang"
    },
    {
      "name": "Yixin Yuan"
    },
    {
      "name": "Yifan Dai"
    },
    {
      "name": "Yufeng Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d795m7bxgg5p1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.19104",
  "fulltext_url": null,
  "id": "d795m7bxgg5p1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.19104",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2613|Advanced Causal Inference Techniques"
    ]
  ],
  "openalex": "W7222035078",
  "pdf_url": "https://arxiv.org/pdf/2610.19104",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d795m7bxgg5p1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:42Z",
      "native_id": "2610.19104",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.19104"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments",
  "title_text": "Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:42Z",
  "url": "https://research.draconitic.com/paper/d795m7bxgg5p1",
  "venue": "arXiv",
  "versions": []
}