Metraipolis › archive › dc_43d63dc2fe05

Transport for Conditional Sampling: Foundations and Applications — arXiv:2611.01436

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01436
License (as archived)
CC0-1.0
Archived
2026-11-03T11:29:00.177Z
SHA-256 of the archived text
2b577f9d3e91de72629c8f07b175848d67e93ce0a325c8d3caf91d9e9f74e46d
Stable URL of this page
https://metraipolis.com/documento/dc_43d63dc2fe05

How to cite

Transport for Conditional Sampling: Foundations and Applications — arXiv:2611.01436 — arXiv (en), https://arxiv.org/abs/2611.01436 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43d63dc2fe05 (Metraipolis archive dc_43d63dc2fe05, sha256 2b577f9d3e91de72629c8f07b175848d67e93ce0a325c8d3caf91d9e9f74e46d)
BibTeX
@misc{dc43d63dc2fe05,
  title = {Transport for Conditional Sampling: Foundations and Applications — arXiv:2611.01436},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01436},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43d63dc2fe05; sha256 2b577f9d3e91de72629c8f07b175848d67e93ce0a325c8d3caf91d9e9f74e46d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01436. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conditional sampling is central to Bayesian inference, generative modeling, and causal inference: given a joint law for random variables $X$ and $Y$ and an observation $Y=y$, one seeks to sample from the conditional law of $X\mid Y=y$. Even when the joint distribution is accurately represented, this task can be computationally difficult as it may require evaluating intractable normalizing constants or solving a new inference problem for each observation. Measure transport provides an approach to this problem by identifying a map with triangular structure that directly pushes forward a reference to the conditional of a joint distribution for any observation. This article reviews the theoretical, methodological, and algorithmic foundations of triangular transports, with the Knothe-Rosenblatt rearrangement as a canonical construction. We discuss methods for estimating triangular maps from finite samples, as well as their use in simulation-based inference and causal inference. While our primary aim is to review existing formulations, we also present new ideas and open questions for conditional sampling using transport.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Methodology (stat.ME) ; Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.01436 — 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 2026-11-03T11:03:22.245Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).