Metraipolis › archive › dc_5fdb7042f0ef
A cylindrical neural approximation theorem for conditional laws of McKean-Vlasov equations with common noise — arXiv:2608.08040
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08040
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:06:57.067Z
- SHA-256 of the archived text
8ee9ac37742fa7c83beafad77174957aa53812cac98b2556e48eb92009a3ae89- Stable URL of this page
https://metraipolis.com/documento/dc_5fdb7042f0ef
How to cite
A cylindrical neural approximation theorem for conditional laws of McKean-Vlasov equations with common noise — arXiv:2608.08040 — arXiv (en), https://arxiv.org/abs/2608.08040 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5fdb7042f0ef (Metraipolis archive dc_5fdb7042f0ef, sha256 8ee9ac37742fa7c83beafad77174957aa53812cac98b2556e48eb92009a3ae89)
BibTeX
@misc{dc5fdb7042f0ef,
title = {A cylindrical neural approximation theorem for conditional laws of McKean-Vlasov equations with common noise — arXiv:2608.08040},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08040},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5fdb7042f0ef; sha256 8ee9ac37742fa7c83beafad77174957aa53812cac98b2556e48eb92009a3ae89},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08040. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce conditional cylindrical neural networks for approximating functionals of conditional laws in McKean-Vlasov equations with common noise. Fourier moments of the initial law and truncated signatures of the time augmented common noise are mapped by a mixture density network to a Gaussian mixture approximation of the conditional law. A cylindrical neural network then evaluates the target functional through analytic integrals against this predicted measure. Rough path well posedness and stability provide a conditional law map that is continuous in the initial distribution and the rough driver and agrees almost surely with the classical conditional law at the Itô Brownian lift. Combining this continuity with Fourier separation, signature uniqueness, Wasserstein density of Gaussian mixtures, and neural universal approximation, we prove an $L^2$ universal approximation theorem for continuous square integrable functionals. The numerical study implements the resulting two stage procedure on six examples, including non Gaussian initial laws, nonlinear drift, multiplicative common noise, and a two dimensional state. Independent particle references are used when no closed form law is available. The learned conditional law and functional approximations consistently improve on the empirical particle plug in, and additional experiments examine feature sensitivity, training from one terminal observation per common noise scenario, and Itô--Stratonovich consistency. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-11 in math.PR). Categorie arXiv: Probability (math.PR) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.08040 — 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 2026-10-19T09:04:32.170Z dalla pagina https://arxiv.org/catchup/math.PR/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).