Metraipolis › archive › dc_fe8c774fb5be
Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking — arXiv:2608.03469
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03469
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:43:16.887Z
- SHA-256 of the archived text
3247b7514b44971f6e7847f025375c4953b7ddcd54ca45ee6ea8af62b25e9964- Stable URL of this page
https://metraipolis.com/documento/dc_fe8c774fb5be
How to cite
Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking — arXiv:2608.03469 — arXiv (en), https://arxiv.org/abs/2608.03469 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe8c774fb5be (Metraipolis archive dc_fe8c774fb5be, sha256 3247b7514b44971f6e7847f025375c4953b7ddcd54ca45ee6ea8af62b25e9964)
BibTeX
@misc{dcfe8c774fb5be,
title = {Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking — arXiv:2608.03469},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03469},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe8c774fb5be; sha256 3247b7514b44971f6e7847f025375c4953b7ddcd54ca45ee6ea8af62b25e9964},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03469. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study score learning for reflected diffusion on bounded domains. Reflection keeps trajectories feasible but does not ensure that the learned score satisfies the boundary behavior implied by the forward process. With implicit score matching, integration by parts leaves a boundary term, and we show that it depends on one scalar at each boundary point: the diffusion- weighted normal component of the score, or conormal trace. The no-flux condition fixes this value while leaving the re- maining boundary components unrestricted; under anisotropic diffusion it generally differs from the ordinary normal score component. On hyperrectangles, our parametrization enforces the required trace without additional trainable parameters or a stochastic boundary estimator and, under regularity assump- tions, can represent the true score, whereas fixing an incorrect value creates an error that more data cannot remove. We ex- tend the construction to simplices and polygonal domains and identify reflection masking: hard reflection can keep samples feasible even when the learned trace is wrong, so post-reflection metrics may hide the error. Experiments show the clearest separation with less frequent reflection, anisotropic diffusion, and mass near intersections of constraints; under full reflection, final sample placement improves inconsistently, illustrating how hard repair can mask boundary-score errors and decouple score accuracy from downstream generation quality. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.03469 — 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 2026-10-31T12:31:30.417Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).