2026
Overcoming PINNs Failure Modes In High Dimension With Low-Rank Fourier Sum
ICML 2026spotlight
Physics-informed neural networks (PINNs) can be unreliable on PDEs with oscillatory, multiscale, stiff, or long-time solutions, and these difficulties worsen in high dimensions where collocation-based training yields large numerical integration error and high-variance gradients. We propose Low-Rank …