Metraipolis › archive › dc_19eec5723fea

Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density — arXiv:2608.16506

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16506
License (as archived)
CC0-1.0
Archived
2026-10-18T19:44:26.135Z
SHA-256 of the archived text
3326e31e9025e3ad8b0a740a6e5b24b2121d536065b3af325c4a8316195dddc8
Stable URL of this page
https://metraipolis.com/documento/dc_19eec5723fea

How to cite

Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density — arXiv:2608.16506 — arXiv (en), https://arxiv.org/abs/2608.16506 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19eec5723fea (Metraipolis archive dc_19eec5723fea, sha256 3326e31e9025e3ad8b0a740a6e5b24b2121d536065b3af325c4a8316195dddc8)
BibTeX
@misc{dc19eec5723fea,
  title = {Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density — arXiv:2608.16506},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16506},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19eec5723fea; sha256 3326e31e9025e3ad8b0a740a6e5b24b2121d536065b3af325c4a8316195dddc8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16506. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dataset alignment is a central step in data analysis across science and engineering, where the goal is to match observations between datasets. Entropic Optimal Transport (EOT) offers a computationally tractable framework for this task by encoding cross-dataset affinities in a transport plan. However, when two datasets are sampled from geometrically similar low-dimensional structures with substantially different sampling densities, the EOT plan may match points by relative sampling density rather than geometric proximity, yielding geometrically misleading correspondences. To address this issue, we propose a density-reweighted EOT framework in which the influence of sampling density on the transport plan can be discounted to a desired degree, ranging from standard EOT to alignment driven purely by underlying geometry. Under suitable regularity conditions, we establish convergence of the reweighted EOT plan to a family of population-level plans whose dependence on sampling density is made explicit. Through simulations, we show that our approach recovers geometrically faithful correspondences, improving over related EOT-based frameworks when datasets exhibit substantial sampling density disparity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Applications (stat.AP); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2608.16506 — 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 2026-10-18T19:02:44.314Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).