CGMPINN combines Gaussian mixture modeling with curriculum learning to reduce training errors in physics-informed neural networks by up to 97.8% on benchmark PDEs while providing theoretical convergence guarantees.
Mitigating propagation failures in physics-informed neural networks using retain- resample-release (R3) sampling
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
-
From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models
CGMPINN combines Gaussian mixture modeling with curriculum learning to reduce training errors in physics-informed neural networks by up to 97.8% on benchmark PDEs while providing theoretical convergence guarantees.