List your company
ResearchFormerly WizWand

PDE Solving on Poisson 1d (test)

0Relative MSENeural Solver
-0.0352780.2031210.441520.679919Oct 9, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Neural SolverTraining Paradigm=Hybrid2024.100——
Neural SolverLearning Paradigm=Neural Solver2024.100.0001——
PINOLearning Paradigm=Hybrid2024.100.0028——
PINOTraining Paradigm=Hybrid2024.100.0033——
PPINNsTraining Paradigm=Unsupervised2024.100.0359——
PPINNsLearning Paradigm=Unsupervised2024.100.043——
PINNS-multi-optLearning Paradigm=Unsupervised2024.100.118——
PI-DeepONetLearning Paradigm=Hybrid2024.100.12——
PI-DeepONetTraining Paradigm=Hybrid2024.100.125——
PO-DeepONetLearning Paradigm=Unsupervised2024.100.143——
MLP + basisLearning Paradigm=Supervised2024.100.15——
P2INNsLearning Paradigm=Unsupervised2024.100.15——
MLP + basisTraining Paradigm=Supervised2024.100.158——
PO-DeepONetTraining Paradigm=Unsupervised2024.100.179——
PINNs+L-BFGSLearning Paradigm=Unsupervised2024.100.883——
Baldwinian-PINNTest task parameters=α1 = 1, α2 = 1, α3 = 0.1, α4 = 0, ω1 = 0.7, ω2 = 1.5, x ∈ [−10, 10], Training task distribution=60 train tasks from α's∈ [0, 4], ω's∈ [0, 4]2023.12—00
NRPINNFine-tuning iterations=900, Test task parameters=α1 = 1, α2 = 1, α3 = 0.1, α4 = 0, ω1 = 0.7, ω2 = 1.5, x ∈ [−10, 10], Training task distribution=60 train tasks from α1 = 1, α2 = 1, α3 = 0.1, α4 = 0, ω1 ∈ [0, 1], ω2 ∈ [0.2]2023.12—0.0005—