Metraipolis › archive › dc_a7dde68df092
Unifying Generative Models with Path Integrals — arXiv:2608.12438
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12438
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:27:17.361Z
- SHA-256 of the archived text
58f1f9f499b78bbeedf27748d4f919c64595adcafdb4c84800f4ef0ced4e7d5b- Stable URL of this page
https://metraipolis.com/documento/dc_a7dde68df092
How to cite
Unifying Generative Models with Path Integrals — arXiv:2608.12438 — arXiv (en), https://arxiv.org/abs/2608.12438 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7dde68df092 (Metraipolis archive dc_a7dde68df092, sha256 58f1f9f499b78bbeedf27748d4f919c64595adcafdb4c84800f4ef0ced4e7d5b)
BibTeX
@misc{dca7dde68df092,
title = {Unifying Generative Models with Path Integrals — arXiv:2608.12438},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12438},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7dde68df092; sha256 58f1f9f499b78bbeedf27748d4f919c64595adcafdb4c84800f4ef0ced4e7d5b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12438. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action. Its Martin-Siggia-Rose-Janssen-de~Dominicis (MSRJD) form separates free from interacting probability flows and opens them to diagrammatic perturbation theory. The expansion yields a one-loop correction to deterministic samplers at no stochastic-sampling cost, which we validate on solvable and nonlinear drifts, where it reduces a 53 % tree-level error to 1.6 %. Imperfect learned scores enter as insertions and yield a response-weighted score-matching objective, and symmetry-equivariant drift design becomes an operator expansion with EFT power counting. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; High Energy Physics - Phenomenology (hep-ph); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2608.12438 — 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 2026-10-19T04:20:35.806Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).