{
  "abstract": "Mutual information (MI) provides an objective for suppressing or encouraging statistical dependence in implicit generative models. However, direct MI evaluation is challenging in implicit models due to typically intractable densities. A remedy is estimating the generator gradient from the difference between conditional and marginal scores. This score difference can, in turn, be estimated by differentiating a log density ratio learned through classification. This construction nevertheless faces two difficulties: (i) singular distributions need not admit the required score functions, and (ii) poor overlap can hinder density-ratio estimation. We therefore introduce Spread Mutual Information (SMI), a weighted integral of MI across noise levels obtained by applying a common spreading kernel to the generated variable. Gaussian spreading yields smooth, strictly positive conditional and marginal densities, extending the gradient construction to distributions that may originally be singular. Across a variaty of experiments, SMI consistently achieves effective dependence control among MI-based methods and remains competitive with established task-specific approaches.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.10021",
  "author_total": 4,
  "authors": [
    {
      "name": "Jiahao Yu"
    },
    {
      "name": "Song Liu"
    },
    {
      "name": "José Miguel Hernández-Lobato"
    },
    {
      "name": "RuiKang OuYang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c5nnkkgq3jfxq.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.10021",
  "fulltext_url": null,
  "id": "c5nnkkgq3jfxq",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.10021",
  "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",
      "1707|Generative Adversarial Networks and Image Synthesis"
    ]
  ],
  "openalex": "W7220979672",
  "pdf_url": "https://arxiv.org/pdf/2610.10021",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c5nnkkgq3jfxq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:48Z",
      "native_id": "2610.10021",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.10021"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Controlling Dependence in Implicit Generative Models via Spread Mutual Information",
  "title_text": "Controlling Dependence in Implicit Generative Models via Spread Mutual Information",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:48Z",
  "url": "https://research.draconitic.com/paper/c5nnkkgq3jfxq",
  "venue": "arXiv",
  "versions": []
}