Research map / Optimization / Implicit bias and generalization
Taming the Loss Landscape of PINNs with Noisy Feynman–Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds
Nathanael Tepakbong, Hanyu HU, Chengyu Liu, Xiang ZHOU
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Poisson PDE | L2 abs error: 1.333 -> 0.761 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Poisson PDE | L2 rel error: 0.322 -> 0.1184 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Poisson PDE | H1 abs error: 12.42 -> 7.822 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Schrödinger-type PDE | L2 abs error: 0.475 -> 0.073 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Schrödinger-type PDE | L2 rel error: 0.624 -> 0.096 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Schrödinger-type PDE | H1 abs error: 2.893 -> 1.043 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Schrödinger-type PDE | H1 rel error: 0.512 -> 0.185 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Mean Escape Time PDE | L2 abs error: 16.56 -> 1.755 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Mean Escape Time PDE | L2 rel error: 1.007 -> 0.107 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Mean Escape Time PDE | H1 rel error: 1.002 -> 0.395 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Committor PDE | L2 abs error: 1.028 -> 0.791 | Improved |
| add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN) | PINN · Committor PDE | L2 rel error: 0.839 -> 0.030 | Improved |
Closest papers by meaning
- Efficient Error Certification for Physics-Informed Neural Networks (ICML 2024 · similarity 0.92)
- Challenges in Training PINNs: A Loss Landscape Perspective (ICML 2024 · similarity 0.91)
- An operator preconditioning perspective on training in physics-informed machine learning (ICLR 2024 · similarity 0.90)
- Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks (NeurIPS 2026 · similarity 0.89)
- PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks (ICLR 2024 · similarity 0.89)
- HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
