A secant-based adaptive correction augments first-order optimizers to improve convergence speed, stability, and accuracy when training PINNs on challenging PDEs.
Regularity and error estimates in physics-informed neural networks for the Kuramoto-Sivashinsky equation
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
-
Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks
A secant-based adaptive correction augments first-order optimizers to improve convergence speed, stability, and accuracy when training PINNs on challenging PDEs.