arXiv Machine Learning
Learning the Structure of Triangular Transport Maps
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Statistics ML
2d ago
Multifidelity Formulations for Triangular Transport
The paper introduces multifidelity techniques for building triangular transport maps when high‑fidelity data are limited but low‑fidelity data are plentiful. Two strategies are proposed: a hierarchical approach that composes maps across fidelity levels, and a non‑hierarchical method that uses monotonicity‑preserving corrections to incorporate low‑fidelity information. Numerical tests show these methods outperform single‑fidelity transport and, when applied to amortized simulation‑based inference, improve conditional sampling and uncertainty quantification in data‑scarce regimes.
arXiv Machine Learning
Jun 30
The Fundamental Limits of Valid Transport Map Estimation
arXiv:2606. 30574v1 Announce Type: new Abstract: Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distributions without explicitly targeting an optimal transport (OT) map.
Hugging Face Trending Papers
Jun 29
The Fundamental Limits of Valid Transport Map Estimation
Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distributions without explicitly targeting an optimal transport (OT) map. In applications like generative modeling, the transport cost itself is irrelevant, and this makes it natural to target maps which are more tractable from either a statistical or computational standpoint.
arXiv Machine Learning
5d ago
Distribution-Conditioned Transport
The paper introduces Distribution‑Conditioned Transport (DCT), a framework that learns transport maps conditioned on embeddings of source and target distributions, allowing generalization to unseen distribution pairs. DCT supports semi‑supervised learning for distributional forecasting by leveraging distributions observed at only one condition. It is agnostic to the transport mechanism and is demonstrated on synthetic benchmarks and four biological applications, including batch effect transfer in single‑cell genomics and modeling T‑cell receptor sequence evolution.
arXiv Machine Learning
Jun 5
Multimarginal flow matching with optimal transport potentials
arXiv:2606. 05327v1 Announce Type: new Abstract: Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions.
arXiv Statistics ML
Sep 10
Manifold-Aligned Generative Transport
arXiv:2602.19600v2 Announce Type: replace Abstract: Many high-dimensional datasets concentrate near a low-dimensional structure embedded in the ambient space. Generative models for such data must con...