Metraipolis › archive › dc_ea92541ce61e
Diffusion Quasi-Monte Carlo — arXiv:2608.11055
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11055
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:27:08.835Z
- SHA-256 of the archived text
b24be82bafb45a378b471a640b6cb973bfa4968660bad167f5acb051d0b5f00c- Stable URL of this page
https://metraipolis.com/documento/dc_ea92541ce61e
How to cite
Diffusion Quasi-Monte Carlo — arXiv:2608.11055 — arXiv (en), https://arxiv.org/abs/2608.11055 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea92541ce61e (Metraipolis archive dc_ea92541ce61e, sha256 b24be82bafb45a378b471a640b6cb973bfa4968660bad167f5acb051d0b5f00c)
BibTeX
@misc{dcea92541ce61e,
title = {Diffusion Quasi-Monte Carlo — arXiv:2608.11055},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11055},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea92541ce61e; sha256 b24be82bafb45a378b471a640b6cb973bfa4968660bad167f5acb051d0b5f00c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11055. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study high-dimensional numerical integration with respect to complex target measures using diffusion-based transport maps and randomized quasi-Monte Carlo (RQMC). Score-based diffusion models induce a deterministic probability flow ODE that transports a simple prior to the target, suggesting a principled way to transform low-discrepancy points on the unit cube into informative samples. We construct a cube-to-target map by composing a Gaussian base transformation (the component-wise inverse Gaussian CDF) with an Euler-discretized probability flow ODE. To retain unbiasedness under transport approximation, we formulate integration as importance sampling (IS) on the cube. Our main result provides verifiable conditions under which the resulting IS integrand satisfies the boundary growth condition, implying an $O(N^{-1+\epsilon})$ RMSE for scrambled nets. We then establish these conditions for diffusion probability-flow transport under mild bounded-derivative assumptions on the learned vector field, explicitly controlling the boundary singularities introduced by the inverse Gaussian CDF. Experiments range from a 2D mixture to 784D images and a 40,960D conditional vorticity-assimilation task; in the latter, blocked scrambled Sobol' sampling reduces the randomization standard deviation of nonlinear accuracy metrics at essentially unchanged online denoising cost. Together, these results give a theoretical and empirical foundation for combining diffusion generative modeling with high-precision RQMC integration.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-12 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.11055 — 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 2026-10-19T06:20:15.719Z dalla pagina https://arxiv.org/catchup/math.NA/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).