General
A kernel method for the learning of Wasserstein geometric flows
arXiv cs.NA0 views
arXiv:2511.06655v3 Announce Type: replace Abstract: Wasserstein gradient and Hamiltonian flows provide geometric formulations of many partial differential equations. We develop a structure-preserving kernel method for jointly estimating the external potential and interaction kernel governing these flows, assuming a known internal energy. The inverse problem is formulated through a trajectory-dependent observation operator and regularized in a product of reproducing kernel Hilbert spaces, yielding an explicit finite representation of the estimator. We characterize joint non-identifiability through the null space of the observation operator and derive a Fourier criterion on the torus, distinguishing uniqueness of the regularized estimator from recovery of the underlying physical components. We establish reconstruction error bounds and convergence rates under source conditions and suitable regularization and mesh refinement, together with a stability estimate for Hamiltonian flows with vanishing internal energy. Numerical experiments demonstrate joint reconstruction and illustrate how unobservable interaction modes can prevent accurate potential recovery despite small observation-equation residuals. A comparison with sparse learning illustrates the dependence of reconstruction accuracy on the chosen dictionary.
Source:https://arxiv.org/abs/2511.06655Related posts
Australia's full national topographic library at your fingertips
0Hacker News
Codeberg seems to have vanished from DNS
0Hacker News New
Codeberg.org Is Down
0Hacker News New
Torrent Infra Needs to Modernize Immediately for Open Models to Survive
0Hacker News New
What if we tried to eat the sun? [video]
0Hacker News New
My Dog Ate a Kitchen Sponge – What to Do Now (Call Your Vet) – PetToxCheck
0Hacker News New