Parameter misspecification in physics-informed neural networks: A closed-form audit and its limits
cs.LG, cs.NA, math.NA, physics.comp-ph
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: 10 pages main body, 3 figures main body, 7 pages supplementary material
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks