Metraipolis › archive › dc_be45e30bbf02

Generative sampling with physics-informed kernels — arXiv:2610.41864

Source

arXiv (en)

Original

https://arxiv.org/abs/2610.41864

License (as archived)

CC0-1.0

Archived

2026-11-03T05:55:49.102Z

SHA-256 of the archived text

0bef0208d333186e60b5e96cc7dcb6278a71f6d8b2a722caacdbf56b43b4a512

Stable URL of this page

https://metraipolis.com/documento/dc_be45e30bbf02

How to cite

Generative sampling with physics-informed kernels — arXiv:2610.41864 — arXiv (en), https://arxiv.org/abs/2610.41864 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be45e30bbf02 (Metraipolis archive dc_be45e30bbf02, sha256 0bef0208d333186e60b5e96cc7dcb6278a71f6d8b2a722caacdbf56b43b4a512)

@misc{dcbe45e30bbf02,
  title = {Generative sampling with physics-informed kernels — arXiv:2610.41864},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41864},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be45e30bbf02; sha256 0bef0208d333186e60b5e96cc7dcb6278a71f6d8b2a722caacdbf56b43b4a512},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41864. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We construct a generative network for Monte-Carlo sampling in lattice field theories and beyond, for which the layerwise propagation is computed and optimised independently on each layer. The architecture uses physics-informed renormalisation group flows that provide access to the layerwise propagation step from one layer to the next in terms of a simple first order partial differential equation for the respective renormalisation group kernel through a given layer. Thus, it transforms the generative task into that of solving once the set of independent and linear differential equations for the kernels of the transformation. As these equations are analytically known, the kernels can be refined iteratively. This allows us to structurally tackle out-of-domain problems generally encountered in generative models and opens the path to further optimisation. We illustrate the practical feasibility of the architecture within simulations in scalar field theories.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv physics.data-an, nuovi lavori del giorno).
Categorie arXiv: High Energy Physics - Lattice (hep-lat) ; Data Analysis, Statistics and Probability (physics.data-an).
Pagina del lavoro: https://arxiv.org/abs/2610.41864 — 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 2026-11-03T05:37:31.968Z dalla pagina https://arxiv.org/list/physics.data-an/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).