GenWGP trains a generative flow to transport mass along Wasserstein gradient paths by optimizing a geometric action loss that encodes the full trajectory and equilibrium, matching reference solutions on Fokker-Planck and aggregation problems with roughly a dozen points.
arXiv preprint arXiv:2412.19520 (2024) 34
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Establishes Transition Path Theory for Lévy-type processes via rigorous SDE representation for transition paths and analysis of their probability distribution, current, and occurrence rate.
citing papers explorer
-
Generative Path-Finding Method for Wasserstein Gradient Flow
GenWGP trains a generative flow to transport mass along Wasserstein gradient paths by optimizing a geometric action loss that encodes the full trajectory and equilibrium, matching reference solutions on Fokker-Planck and aggregation problems with roughly a dozen points.
-
Transition Path Theory For L\'{e}vy-Type Processes: SDE Representation and Statistics
Establishes Transition Path Theory for Lévy-type processes via rigorous SDE representation for transition paths and analysis of their probability distribution, current, and occurrence rate.