The authors introduce an energy-based learning method grounded in the De Giorgi dissipation functional that infers potential energies for generalized diffusions while preserving variational structure and showing improved robustness to noise and limited observations.
Title resolution pending
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
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.
citing papers explorer
-
Structure-Aware Variational Learning of a Class of Generalized Diffusions
The authors introduce an energy-based learning method grounded in the De Giorgi dissipation functional that infers potential energies for generalized diffusions while preserving variational structure and showing improved robustness to noise and limited observations.
-
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.