Metraipolis › archive › dc_88cebc226131

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
2026-11-02T04:51:36.345Z
SHA-256 of the archived text
3a5bdd8a4dccf38e3d12b08f76768fa5771d31ca16bf14ef657b496be5f23889
Stable URL of this page
https://metraipolis.com/documento/dc_88cebc226131

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_88cebc226131 (Metraipolis archive dc_88cebc226131, sha256 3a5bdd8a4dccf38e3d12b08f76768fa5771d31ca16bf14ef657b496be5f23889)
BibTeX
@misc{dc88cebc226131,
  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_88cebc226131; sha256 3a5bdd8a4dccf38e3d12b08f76768fa5771d31ca16bf14ef657b496be5f23889},
  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 2026-11-02T04:45:12.878Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).