[
    {
        "id": "osp-16636",
        "type": "article-journal",
        "title": "Controlling Dependence in Implicit Generative Models via Spread Mutual Information",
        "author": [
            {
                "family": "Yu",
                "given": "Jiahao"
            },
            {
                "family": "Liu",
                "given": "Song"
            },
            {
                "family": "Hernández-Lobato",
                "given": "José Miguel"
            },
            {
                "family": "OuYang",
                "given": "RuiKang"
            }
        ],
        "URL": "https://omanscience.com/en/articles/controlling-dependence-in-implicit-generative-models-via-spread-mutual-information",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]