arXiv stat.ML
· Papers
Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks
arXiv:2605.07060v3 Announce Type: replace-cross Abstract: Physics-informed neural networks (PINNs) provide a mesh-free framework for solving PDE-constrained inverse problems, but their extension to Bayesian inversion still faces a fundamental difficulty: prior distributions are typically defined in the weight space of