Parameterized Time-Dependent Allen-Cahn Equation Solving (100D)
0.0016Relative L1 ErrorDeepSplitting
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSplittingParadigm=Retrain per μ2026.06 | 0.0016 | |
| DeepBSDEParadigm=Retrain per μ2026.06 | 0.0025 | |
| PRISM-SDGDParadigm=Zero-Shot ∀μ2026.06 | 0.0044 | |
| PRISM-STDEParadigm=Zero-Shot ∀μ2026.06 | 0.0044 |