{
  "abstract": "Modern machine learning depends heavily on massive datasets, but obtaining high-quality annotations at scale is often expensive. As a result, learning from noisily-labeled data has become common, making accurate estimation of the label-noise transition matrix crucial. However, existing transition matrix estimators rely on the fragile estimation of class-posteriors and do not provide finite-sample performance guarantees. In this work, we propose a novel methodology to estimate the transition matrix based on one-sided selective classification. This approach bypasses class-posterior estimation, provides finite-sample performance guarantees, and leverages flexible learning methods for binary classification. Moreover, we introduce effective algorithms to implement the proposed methodology and provide their refined finite-sample performance bounds.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.39829",
  "author_total": 4,
  "authors": [
    {
      "name": "Xabier de Juan"
    },
    {
      "name": "Santiago Mazuelas"
    },
    {
      "name": "Yilun Zhu"
    },
    {
      "name": "Clayton Scott"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/aa7n1qsdn2zqc.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.39829",
  "fulltext_url": null,
  "id": "aa7n1qsdn2zqc",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.39829",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning and Data Classification"
    ]
  ],
  "openalex": "W7215062549",
  "pdf_url": "https://arxiv.org/pdf/2609.39829",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/aa7n1qsdn2zqc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:58Z",
      "native_id": "2609.39829",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.39829"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification",
  "title_text": "Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:58Z",
  "url": "https://research.draconitic.com/paper/aa7n1qsdn2zqc",
  "venue": "arXiv",
  "versions": []
}