Physics-based active learning using PDE residuals improves data efficiency for neural operator training on Burgers and Navier-Stokes equations while adding a physics inductive bias.
Qianying Cao, Somdatta Goswami, and George Em Karniadakis
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
-
Data-Efficient Neural Operator Training via Physics-Based Active Learning
Physics-based active learning using PDE residuals improves data efficiency for neural operator training on Burgers and Navier-Stokes equations while adding a physics inductive bias.