Metraipolis › archive › dc_9ee16830b3eb

Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO Scheme — arXiv:2610.10278

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10278
License (as archived)
CC0-1.0
Archived
2026-10-08T12:37:29.445Z
SHA-256 of the archived text
9c3c40c7df0f5c1ead56c8b23b9145ad6e4afd78162872182b241762ec70743a
Stable URL of this page
https://metraipolis.com/documento/dc_9ee16830b3eb

How to cite

Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO Scheme — arXiv:2610.10278 — arXiv (en), https://arxiv.org/abs/2610.10278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ee16830b3eb (Metraipolis archive dc_9ee16830b3eb, sha256 9c3c40c7df0f5c1ead56c8b23b9145ad6e4afd78162872182b241762ec70743a)
BibTeX
@misc{dc9ee16830b3eb,
  title = {Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO Scheme — arXiv:2610.10278},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10278},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ee16830b3eb; sha256 9c3c40c7df0f5c1ead56c8b23b9145ad6e4afd78162872182b241762ec70743a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a neural algorithm for sampling from distributions specified by unnormalized Boltzmann densities. Our approach is based on the Jordan--Kinderlehrer--Otto scheme for the Kullback--Leibler divergence in the Wasserstein--Fisher--Rao geometry (WFR JKO scheme). Our contributions are twofold. First, we prove that, for any fixed step size, the exact WFR JKO iterates converge exponentially fast to the target as the number of iterations tends to infinity. Notably, this result requires no structural assumptions on the target, such as log-concavity or a logarithmic Sobolev inequality. Second, we develop a neural implementation of the WFR JKO scheme that parametrizes its transport and reaction components using reweighted normalizing flows. Numerical experiments on challenging multimodal targets demonstrate the promising performance of the proposed method.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG); Probability (math.PR); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.10278 — 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 2026-10-08T12:14:15.459Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).