Metraipolis › archive › dc_37909f2a1ccf
Branched Optimal Transport Amortization — arXiv:2609.15072
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15072
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:53:35.745Z
- SHA-256 of the archived text
8be316c0292f20117f91b7d533f0fac83839cc72a3c07a45b579c9cc7881407f- Stable URL of this page
https://metraipolis.com/documento/dc_37909f2a1ccf
How to cite
Branched Optimal Transport Amortization — arXiv:2609.15072 — arXiv (en), https://arxiv.org/abs/2609.15072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37909f2a1ccf (Metraipolis archive dc_37909f2a1ccf, sha256 8be316c0292f20117f91b7d533f0fac83839cc72a3c07a45b579c9cc7881407f)
BibTeX
@misc{dc37909f2a1ccf,
title = {Branched Optimal Transport Amortization — arXiv:2609.15072},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15072},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37909f2a1ccf; sha256 8be316c0292f20117f91b7d533f0fac83839cc72a3c07a45b579c9cc7881407f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15072. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Methods of Branched Optimal Transport (BOT) mimic the economy and efficiency of natural tree-like structures, such as those found in rivers and biological systems. These methods are widely applicable for designing efficient networks in society, from river basins and blood vessels to mail and gas distribution systems. However, they remain understudied in the context of designing deep generative models, particularly at a large scale. Standard continuous-time generative models, such as the flow matching approach, fail to capture the inherent hierarchical and branching patterns present in real-world data. Current models provide no mechanism for flows to merge or share pathways to minimize total transport cost. Inspired by the "economy of scale" principle in BOT, we introduce a novel, scalable branched flow-matching algorithm designed to solve the branched optimal transport problem in high dimensions. Our method adapts the Benamou-Brenier continuous-time optimal transport formulation to learn branched generative flows. These flows allow probability mass to aggregate along common pathways before branching out to diverse targets. Parametrized by neural networks, our method effectively learns complex branched generative processes. We demonstrate its effectiveness on challenging high-dimensional tasks in biology and image generation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.15072 — 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 2026-10-15T22:29:03.797Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).