Conditional Wasserstein distances with applications in Bayesian OT flow matching

MaRDI QIDQ6887415zbMATH OpenFDO

Authors Jannis Chemseddine, Paul Hagemann, Gabriele Steidl, Christian Wald

Publication date 9 December 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/24-0586.html

zbMATH Keywords

conditional Wasserstein distanceflow matchinggenerative modellinginverse problemsposterior sampling

Mathematics Subject Classification ID

Optimal transportation (49Q22) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A Connection Between Score Matching and Denoising Autoencoders
• A convexity principle for interacting gases
• Computational optimal transport. With applications to data sciences
• Contributions to the theory of convex bodies
• Data driven conditional optimal transport
• Estimation of non-normalized statistical models by score matching
• Extensions with shrinking fibers
• Generalized Normalizing Flows via Markov Chains
• Heterogeneous gradient flows in the topology of fibered optimal transport
• scientific article; zbMATH DE number 2152346 (Why is no real title available?)
• scientific article; zbMATH DE number 5174522 (Why is no real title available?)
• Lectures on optimal transport
• Optimal Transport
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Optimal transport for conditional domain matching and label shift
• Remarks on a Multivariate Transformation
• Stochastic normalizing flows for inverse problems: a Markov chains viewpoint

Cited in

(1)

• DAWN-FM: data-aware and noise-informed flow matching for solving inverse problems

This page was built for publication: Conditional Wasserstein distances with applications in Bayesian OT flow matching

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6887415)