With a carefully chosen step size, finite-difference derivatives match automatic differentiation in accuracy and beat it in speed and memory for MLP-based physics-informed neural networks.
Jiaming Zhang, David Dalton, Hao Gao, and Dirk Husmeier
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond
With a carefully chosen step size, finite-difference derivatives match automatic differentiation in accuracy and beat it in speed and memory for MLP-based physics-informed neural networks.