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
Your Bash Script Checked the Quantity With -eq and the Quantity Ran a Command
0dev.to Linux
The Gödel Editorial Project: A Synopsis (2005, Pdf)
0Hacker News New
The Complete Guide to the into the Wild Bus [2022 Tribute]
0Hacker News New
Morphic Resonance and Morphic Fields
0Hacker News New
Stoolap 0.5.0: One Query, One Answer
0Hacker News New
I gave Claude Code a memory and it used 26% fewer tokens
0Hacker News New