Metraipolis › archive › dc_ea5fec37626e

Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality — arXiv:2609.06598

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06598
License (as archived)
CC0-1.0
Archived
2026-10-16T13:57:07.853Z
SHA-256 of the archived text
bd0a38f89f13d6060c29aae9f5c038e243b51b903f8cb39335c879b96c3aaa7f
Stable URL of this page
https://metraipolis.com/documento/dc_ea5fec37626e

How to cite

Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality — arXiv:2609.06598 — arXiv (en), https://arxiv.org/abs/2609.06598 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea5fec37626e (Metraipolis archive dc_ea5fec37626e, sha256 bd0a38f89f13d6060c29aae9f5c038e243b51b903f8cb39335c879b96c3aaa7f)
BibTeX
@misc{dcea5fec37626e,
  title = {Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality — arXiv:2609.06598},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06598},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea5fec37626e; sha256 bd0a38f89f13d6060c29aae9f5c038e243b51b903f8cb39335c879b96c3aaa7f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06598. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The optimal transport (OT) map provides a geometric transformation for aligning probability distributions and has become a useful tool in machine learning. However, existing estimators of the OT map still exhibit a gap between sharp statistical guarantees and practical parametric estimation based on stable training objectives. Theoretical estimators achieve minimax optimal convergence rates, but they are typically nonparametric and can incur demanding implementation design or inference costs. Practical estimators are parametric and scalable, but their statistical guarantees remain underexplored, and their min-max, adversarial-like training objectives can be sensitive to optimization algorithms. We propose BROT (Barycentric Regression for OT), a simple two-step method that first computes the unregularized OT plan and then fits a deep neural network (DNN) to the induced barycentric targets by least-squares regression. Under standard regularity conditions, we prove that the DNN estimator of BROT attains the minimax convergence rate, when the ground-truth OT map is Lipschitz. Numerical studies on synthetic datasets and an image dataset show that BROT provides accurate map estimates, strong target distribution matching, and competitive transport costs, compared to existing estimation methods. Experiments on two downstream tasks, single-cell perturbation prediction and unsupervised domain adaptation, further suggest that the accurate estimation of BROT can translate into stronger task performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.06598 — 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 2026-10-16T13:39:42.898Z 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).