Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
arXiv preprint arXiv:2506.01502 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
NGIF leverages gauge freedom in the continuity equation to learn non-gradient vector fields, improving distributional accuracy and non-potential transport capture over gradient-restricted baselines on low- and high-dimensional physics problems.
citing papers explorer
-
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
-
Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
NGIF leverages gauge freedom in the continuity equation to learn non-gradient vector fields, improving distributional accuracy and non-potential transport capture over gradient-restricted baselines on low- and high-dimensional physics problems.