A bidirectional DeepParticle method for efficiently solving low-dimensional transport map problems

DOI10.1016/J.JCP.2026.114983MaRDI QIDQ7312100zbMATH OpenFDO

Authors Tan Zhang, Zhongjian Wang, Jack Xin, Zhiwen Zhang

Publication date 11 August 2026

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2026.114983

Mathematics Subject Classification ID

Partial differential equations of mathematical physics and other areas of application (35Qxx) Calculus of variations and optimal control; optimization (49-XX) Manifolds and measure-geometric topics (49Qxx)

Cites work

• A DeepParticle method for learning and generating aggregation patterns in multi-dimensional Keller-Segel chemotaxis systems
• A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
• An invitation to optimal transport, Wasserstein distances, and gradient flows
• Data-driven optimal transport
• DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method
• Generative ensemble regression: Learning particle dynamics from observations of ensembles with physics-informed deep generative models
• Initiation of slime mold aggregation viewed as an instability
• Learning to match via inverse optimal transport
• Lectures on optimal transport
• Normalizing flows for probabilistic modeling and inference
• On the rate of convergence in Wasserstein distance of the empirical measure
• Optimal transport: fast probabilistic approximation with exact solvers
• Unnormalized optimal transport

This page was built for publication: A bidirectional DeepParticle method for efficiently solving low-dimensional transport map problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7312100)