Metraipolis › archive › dc_db524e604eed

Shrinkage prior for implicit generative models — arXiv:2611.05241

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05241
License (as archived)
CC0-1.0
Archived
2026-11-04T21:52:28.199Z
SHA-256 of the archived text
fb4d1628668f7b2b07299ef8a2b209c4ca28f3595cfd8c2ef2f0d44dfc7d1bdc
Stable URL of this page
https://metraipolis.com/documento/dc_db524e604eed

How to cite

Shrinkage prior for implicit generative models — arXiv:2611.05241 — arXiv (en), https://arxiv.org/abs/2611.05241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db524e604eed (Metraipolis archive dc_db524e604eed, sha256 fb4d1628668f7b2b07299ef8a2b209c4ca28f3595cfd8c2ef2f0d44dfc7d1bdc)
BibTeX
@misc{dcdb524e604eed,
  title = {Shrinkage prior for implicit generative models — arXiv:2611.05241},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05241},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db524e604eed; sha256 fb4d1628668f7b2b07299ef8a2b209c4ca28f3595cfd8c2ef2f0d44dfc7d1bdc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Implicit generative models based on deep neural networks have revolutionized many scientific fields, from weather research to language generation. They successfully model complex random objects arising in real-world problems. In this work, we propose a sample-efficient training mechanism for these models. Our approach leverages regularized inference with shrinkage priors and generalized Bayes. In the large $p$ (parameter dimension) and small $n$ (sample size) setting, sparsity-inducing priors have been successfully used for linear regression when $p \gg n$. However, their application to implicit generative models remains challenging due to the intractability of the likelihood function. To address this, we adapt a scoring rule posterior based on a strictly proper scoring rule, following the generalized Bayes framework. We then propose a block SGMCMC within Gibbs sampling mechanism. This enables efficient exploration of high-dimensional parameter spaces by identifying a sparse representation of neural implicit generative models. We demonstrate the performance of our proposed method through experiments on $p \gg n$ linear regression and an application of neural generative models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2611.05241 — 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 2026-11-04T21:38:49.764Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).