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
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.