Metraipolis › archive › dc_7f9f8335db65
ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto Front — arXiv:2609.07706
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07706
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:57:54.520Z
- SHA-256 of the archived text
43cde8a282e864aced1bf512028ce90209757e37aef290636bf382741c566838- Stable URL of this page
https://metraipolis.com/documento/dc_7f9f8335db65
How to cite
ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto Front — arXiv:2609.07706 — arXiv (en), https://arxiv.org/abs/2609.07706 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f9f8335db65 (Metraipolis archive dc_7f9f8335db65, sha256 43cde8a282e864aced1bf512028ce90209757e37aef290636bf382741c566838)
BibTeX
@misc{dc7f9f8335db65,
title = {ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto Front — arXiv:2609.07706},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07706},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f9f8335db65; sha256 43cde8a282e864aced1bf512028ce90209757e37aef290636bf382741c566838},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07706. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Offline multi-objective optimization requires not only moving the objective vectors of candidate designs toward the Pareto front, but also distributing them effectively along it. Generative methods have recently emerged as a natural approach because they learn a distribution over feasible designs while allowing generation to be steered toward promising designs. Existing methods, however, largely retain classical sample-wise guidance strategies, leaving the distribution-level modeling capability of generative methods underused. We propose ParetoTransport, a training-free guidance method for pre-trained flow-matching models that explicitly specifies and refines a population-level distribution in objective space. ParetoTransport guides a flow-matching sampler to iteratively transport the empirical offline distribution toward the Pareto front, with Wasserstein matching to intermediate proxy distributions. This directly controls distributional displacement and mass allocation along the front. We establish a convergence result and demonstrate state-of-the-art performance on standard offline MOO benchmarks, extending recent evaluations beyond hypervolume to generational distance, inverted generational distance, and Wasserstein distance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.07706 — 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 2026-10-16T13:39:42.983Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).