Metraipolis › archive › dc_50d2d892c833

Generative bootstrap processes — arXiv:2609.13471

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13471
License (as archived)
CC0-1.0
Archived
2026-10-16T01:11:46.231Z
SHA-256 of the archived text
f8d213ffe44428e4ee4fde5d8c4e753ddf8e9b6ee581e086b5d00cdd55fe92a0
Stable URL of this page
https://metraipolis.com/documento/dc_50d2d892c833

How to cite

Generative bootstrap processes — arXiv:2609.13471 — arXiv (en), https://arxiv.org/abs/2609.13471 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50d2d892c833 (Metraipolis archive dc_50d2d892c833, sha256 f8d213ffe44428e4ee4fde5d8c4e753ddf8e9b6ee581e086b5d00cdd55fe92a0)
BibTeX
@misc{dc50d2d892c833,
  title = {Generative bootstrap processes — arXiv:2609.13471},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13471},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50d2d892c833; sha256 f8d213ffe44428e4ee4fde5d8c4e753ddf8e9b6ee581e086b5d00cdd55fe92a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13471. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study generative bootstrap processes obtained by resampling from fitted generative distributions. We establish necessary and sufficient conditions for their conditional weak convergence to the $P$-Brownian bridge, formulated in terms of finite-dimensional conditional weak convergence and conditional asymptotic equicontinuity. We further provide general sufficient conditions and a Giné-Zinn-type characterization relating this convergence to the $P$-Donsker property. As applications, we verify these conditions for prominent classes of generative models, including triangular normalizing flows, flow matching, score-based diffusion models, and Wasserstein generative adversarial networks.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-15 in math.ST).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.13471 — 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 2026-10-16T00:31:08.644Z dalla pagina https://arxiv.org/catchup/math.ST/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).