{
  "abstract": "Measuring statistical dependency between high-dimensional random variables is a fundamental task in data science and machine learning. Neural mutual information (MI) estimators offer a promising avenue, but they typically require costly iterative optimization for each new dataset, making them impractical for real-time applications. We present InfoAtlas, a foundation model-like architecture that eliminates this bottleneck by directly inferring MI in a single forward pass. Pretrained on large-scale synthetic data with rich dependence patterns, InfoAtlas learns to identify diverse dependence structures and predict MI directly from the dataset. Comprehensive experiments demonstrate that InfoAtlas matches state-of-the-art neural estimators in accuracy while achieving $100\\times$ speedup, can flexibly handle varying dimensions and sample sizes through a single unified model, and generalizes effectively to complex, real-world scenarios. By reformulating MI estimation as an inference task, InfoAtlas establishes a foundation for real-time dependency analysis.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.00241",
  "author_total": 8,
  "authors": [
    {
      "name": "Zhengyang Hu"
    },
    {
      "name": "Yanzhi Chen"
    },
    {
      "name": "Hanxiang Ren"
    },
    {
      "name": "Qunsong Zeng"
    },
    {
      "name": "Youyi Zheng"
    },
    {
      "name": "Adrian Weller"
    },
    {
      "name": "Kaibin Huang"
    },
    {
      "name": "Yanchao Yang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8nt5j61cghwzz.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.00241",
  "fulltext_url": null,
  "id": "8nt5j61cghwzz",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.00241",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Neural Networks and Applications"
    ]
  ],
  "openalex": "W7163169930",
  "pdf_url": "https://arxiv.org/pdf/2606.00241",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8nt5j61cghwzz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:36Z",
      "native_id": "2606.00241",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.00241"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate",
  "title_text": "InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:36Z",
  "url": "https://research.draconitic.com/paper/8nt5j61cghwzz",
  "venue": "arXiv",
  "versions": []
}