Metraipolis › archive › dc_bcb83f62331f
Generative SDEs with Trainable Diffusion and Density-Based Losses — arXiv:2610.41243
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41243
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:40:45.364Z
- SHA-256 of the archived text
ce5902dcd513a5ad2b2f84e29f3344642370d47aa0bad1f4e891500f131c25bd- Stable URL of this page
https://metraipolis.com/documento/dc_bcb83f62331f
How to cite
Generative SDEs with Trainable Diffusion and Density-Based Losses — arXiv:2610.41243 — arXiv (en), https://arxiv.org/abs/2610.41243 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcb83f62331f (Metraipolis archive dc_bcb83f62331f, sha256 ce5902dcd513a5ad2b2f84e29f3344642370d47aa0bad1f4e891500f131c25bd)
BibTeX
@misc{dcbcb83f62331f,
title = {Generative SDEs with Trainable Diffusion and Density-Based Losses — arXiv:2610.41243},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41243},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcb83f62331f; sha256 ce5902dcd513a5ad2b2f84e29f3344642370d47aa0bad1f4e891500f131c25bd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41243. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop a divergence-kernel method for jointly optimizing neural SDE drift and diffusion fields and the initial Gaussian distribution, using losses that depend directly on the terminal density. In two- and eight-dimensional Gaussian-mixture experiments, we learn time-independent fields and obtain far fewer off-mode samples than score-based generators with similar parameter counts. The drift attracts samples toward the modes, while the diffusion helps disperse excess probability between them. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Dynamical Systems (math.DS). Pagina del lavoro: https://arxiv.org/abs/2610.41243 — 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 2026-11-03T05:26:25.676Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).