{
  "abstract": "Neural quantum states based on modern deep learning architectures have emerged as powerful representations for quantum many-body systems. In particular, Transformer-based neural quantum states provide expressive models capable of capturing long-range correlations, and their empirical generalization performance has recently been demonstrated. However, a theoretical understanding of their generalization behavior remains largely unexplored. In this paper, we develop a theoretical framework to analyze the generalization properties of Transformer-based neural quantum states under in-context learning. We establish a rigorous inference-time generalization error bound in terms of mean squared error (MSE), showing that the pointwise prediction error decreases inversely with both the number of in-context examples and the depth of the Transformer. We further show that the Transformer depth required to achieve this guarantee scales only linearly with the system size--namely, the number of particles in continuous systems or the number of qudits in discrete systems. Building on this result, we extend our analysis to full quantum states formulated as rank-one density operators, and derive MSE-based generalization bounds over both continuous and discrete domains under physical constraints. Finally, numerical simulations corroborate our theoretical analysis.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.03463",
  "author_total": 3,
  "authors": [
    {
      "name": "Zhen Qin"
    },
    {
      "name": "Qing Qu"
    },
    {
      "name": "Alfred O. Hero III"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7gsqm25dfadhd.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.03463",
  "fulltext_url": null,
  "id": "7gsqm25dfadhd",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.03463",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "3107|Quantum many-body systems"
    ]
  ],
  "openalex": "W7220437726",
  "pdf_url": "https://arxiv.org/pdf/2610.03463",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7gsqm25dfadhd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:45Z",
      "native_id": "2610.03463",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.03463"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "Generalization of Transformer-Based Neural Quantum States via In-Context Learning",
  "title_text": "Generalization of Transformer-Based Neural Quantum States via In-Context Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:45Z",
  "url": "https://research.draconitic.com/paper/7gsqm25dfadhd",
  "venue": "arXiv",
  "versions": []
}