A learned continuous Lagrangian paired with Euler-Lagrange residual minimization on local patches enables stable long-range forecasting of PDE-governed systems while generalizing across boundary conditions.
Advances in Neural Information Processing Systems (NeurIPS) , volume=
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
-
Learned Lagrangian Models of PDEs via Euler-Lagrange Residual Minimization
A learned continuous Lagrangian paired with Euler-Lagrange residual minimization on local patches enables stable long-range forecasting of PDE-governed systems while generalizing across boundary conditions.