Metraipolis › archive › dc_f522c7f8019f

Controlling Dependence in Implicit Generative Models via Spread Mutual Information — arXiv:2610.10021

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10021
License (as archived)
CC0-1.0
Archived
2026-10-08T12:37:14.571Z
SHA-256 of the archived text
5e34c7a00b7b36ce28ceb835f66a054ec66b1bb48e1020b79dbf8e23f7727903
Stable URL of this page
https://metraipolis.com/documento/dc_f522c7f8019f

How to cite

Controlling Dependence in Implicit Generative Models via Spread Mutual Information — arXiv:2610.10021 — arXiv (en), https://arxiv.org/abs/2610.10021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f522c7f8019f (Metraipolis archive dc_f522c7f8019f, sha256 5e34c7a00b7b36ce28ceb835f66a054ec66b1bb48e1020b79dbf8e23f7727903)
BibTeX
@misc{dcf522c7f8019f,
  title = {Controlling Dependence in Implicit Generative Models via Spread Mutual Information — arXiv:2610.10021},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10021},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f522c7f8019f; sha256 5e34c7a00b7b36ce28ceb835f66a054ec66b1bb48e1020b79dbf8e23f7727903},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.10021 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:14:15.435Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).