Metraipolis › archive › dc_b69de3cd82d8
Neural Renormalization Group Flow for Percolation — arXiv:2608.26764
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26764
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:15:51.441Z
- SHA-256 of the archived text
feba2f0f9ac9dd1500d0829609ba1b8d2237ed8153cefeda294d8a8adfa683db- Stable URL of this page
https://metraipolis.com/documento/dc_b69de3cd82d8
How to cite
Neural Renormalization Group Flow for Percolation — arXiv:2608.26764 — arXiv (en), https://arxiv.org/abs/2608.26764 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b69de3cd82d8 (Metraipolis archive dc_b69de3cd82d8, sha256 feba2f0f9ac9dd1500d0829609ba1b8d2237ed8153cefeda294d8a8adfa683db)
BibTeX
@misc{dcb69de3cd82d8,
title = {Neural Renormalization Group Flow for Percolation — arXiv:2608.26764},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26764},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b69de3cd82d8; sha256 feba2f0f9ac9dd1500d0829609ba1b8d2237ed8153cefeda294d8a8adfa683db},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26764. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine learning offers a possible route to data-driven real-space renormalization when the relevant observables are nonlocal and difficult to prescribe explicitly. We explore this idea for two-dimensional site percolation developping a supervised, scale-shared neural architecture. The model recursively applies the same learned coarse-graining rule across scales, producing a latent field from which the crossing probability is predicted, while a corresponding fine-graining decoder reconstructs the largest-cluster mask. Trained only on small lattices, the model extrapolates to substantially larger systems, recovers the spanning cluster with high fidelity, and produces observables obeying the expected finite-size scaling near the critical point. We observe that to get such performance it is key that the learned latent representation exhibits critical fluctuations and scale-dependent flows consistent with the renormalization-group structure of percolation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG). Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.26764 — 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 2026-10-17T15:34:50.001Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).