Metraipolis › archive › dc_d6a80dbf77a2

A Splitting Method for SDE Terminal-Law Estimation — arXiv:2609.12513

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12513
License (as archived)
CC0-1.0
Archived
2026-10-16T03:16:08.263Z
SHA-256 of the archived text
06ad006b31008ea47b3d5b3d1f96e2bf7c68553f353d766c5355c000e5d93c05
Stable URL of this page
https://metraipolis.com/documento/dc_d6a80dbf77a2

How to cite

A Splitting Method for SDE Terminal-Law Estimation — arXiv:2609.12513 — arXiv (en), https://arxiv.org/abs/2609.12513 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d6a80dbf77a2 (Metraipolis archive dc_d6a80dbf77a2, sha256 06ad006b31008ea47b3d5b3d1f96e2bf7c68553f353d766c5355c000e5d93c05)
BibTeX
@misc{dcd6a80dbf77a2,
  title = {A Splitting Method for SDE Terminal-Law Estimation — arXiv:2609.12513},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12513},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d6a80dbf77a2; sha256 06ad006b31008ea47b3d5b3d1f96e2bf7c68553f353d766c5355c000e5d93c05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12513. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In many settings involving stochastic differential equations, including in diffusion based generative AI, our aim is to accurately generate samples from a terminal distribution. Typically, this is done by generating i.i.d. samples of diffusion paths. Given a fixed simulation budget, a reasonable way to gain efficiency may be to instead generate a tree of paths through appropriately split partial paths. This suggests improved performance, but one worries about the injected dependence. In this paper, we study this issue comprehensively. With Kolmogorov-Smirnov distance as a measure of accuracy, we identify the limiting errors of the associated empirical distributions as the simulation budget increases to infinity. We characterize a splitting strategy motivated by a corresponding asymptotic optimization problem. The theoretical results bring out the elegant underlying structure in the problem. Practical implementation involves two phases, an initial estimation phase and a final inference phase. Overall, we observe a 10-25% improvement in mean error over i.i.d. samples in many settings. In an exploratory CIFAR-10 study, our method reduces the maximum mean discrepancy by 8-13%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.12513 — 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 2026-10-16T03:05:44.106Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).