STAP reduces training data costs for PDE surrogates by selectively acquiring key time steps per trajectory instead of full simulations.
Active learning for neural pde solvers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
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.
A differentiable neural operator learns the mapping from granular microstructure configurations to failure envelopes, with physics-informed convexity enforcement and active learning for efficient training.
citing papers explorer
-
Active Learning with Selective Time-Step Acquisition for PDEs
STAP reduces training data costs for PDE surrogates by selectively acquiring key time steps per trajectory instead of full simulations.
-
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.
-
Neural Operator Representation of Granular Micromechanics-based Failure Envelope
A differentiable neural operator learns the mapping from granular microstructure configurations to failure envelopes, with physics-informed convexity enforcement and active learning for efficient training.