{
  "abstract": "This paper studies transfer learning for high-dimensional quantile regression with limited target samples and heterogeneous source domains. We propose a sample-level transfer learning method (SL-TL) that combines sample selection and importance weighting. Unlike existing source-level approaches that include or exclude entire source domains, SL-TL identifies transferable samples within each source domain and incorporates them through adaptive importance weights. The proposed weights rely only on one-dimensional densities associated with the quantile loss, avoiding the estimation of high-dimensional density ratios. We establish error bounds for SL-TL estimators and characterize the effective sample size contributed by source domains. In the oracle setting, we show that SL-TL achieves faster $\\ell_2$-convergence rates than existing competitors under the considered regimes. For the unknown setting, we develop an implementable algorithm based on sample splitting and cross-fitting procedures. Extensive simulations and a real data analysis demonstrate the finite-sample performance and robustness of SL-TL.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.09722",
  "author_total": 3,
  "authors": [
    {
      "name": "Xiangyu Xing"
    },
    {
      "name": "Yingxuan Wang"
    },
    {
      "name": "Wangli Xu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/69hdhdwdpwzs7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.09722",
  "fulltext_url": null,
  "id": "69hdhdwdpwzs7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.09722",
  "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",
      "stat.ME"
    ],
    [
      "openalex",
      "1702|Domain Adaptation and Few-Shot Learning"
    ]
  ],
  "openalex": "W7220931976",
  "pdf_url": "https://arxiv.org/pdf/2610.09722",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/69hdhdwdpwzs7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:48Z",
      "native_id": "2610.09722",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.09722"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "Beyond Source-Level Transfer: Sample-Level Learning for High-Dimensional Quantile Regression",
  "title_text": "Beyond Source-Level Transfer: Sample-Level Learning for High-Dimensional Quantile Regression",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:48Z",
  "url": "https://research.draconitic.com/paper/69hdhdwdpwzs7",
  "venue": "arXiv",
  "versions": []
}