{
  "abstract": "We extend recent work establishing an equivalence between one-layer transformers and nearest-neighbor classifiers in the binary setting to the multiclass case. By leveraging the simplex encoding, we show that one-layer transformers with an argmax classification head behave identically to a one-nearest-neighbor classifier in the multiclass setting. This closes a gap left by prior work, whose multiclass result relied on a non-standard rounding-based approach rather than the typical argmax head used in practice.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.01311",
  "author_total": 2,
  "authors": [
    {
      "name": "Skanda Athreya"
    },
    {
      "name": "Yutong Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cm93b1dpcrkfy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.01311",
  "fulltext_url": null,
  "id": "cm93b1dpcrkfy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.01311",
  "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.ML"
    ],
    [
      "openalex",
      "1702|Neural Networks and Applications"
    ]
  ],
  "openalex": "W7206218430",
  "pdf_url": "https://arxiv.org/pdf/2609.01311",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cm93b1dpcrkfy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:10Z",
      "native_id": "2609.01311",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.01311"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context",
  "title_text": "One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:10Z",
  "url": "https://research.draconitic.com/paper/cm93b1dpcrkfy",
  "venue": "arXiv",
  "versions": []
}