AI RESEARCH
Gradient Scaling Effects in Adaptive Spectral PINNs for Stiff Nonlinear ODEs
arXiv CS.LG
•
ArXi:2605.04502v1 Announce Type: new Physics-Informed Neural Networks (PINNs) often struggle to train reliably on stiff and oscillatory dynamical systems due to poor optimization conditioning. While prior work has emphasized representational remedies such as spectral parameterizations, the optimization implications of initial-condition (IC) embeddings in adaptive spectral PINNs have not been well characterized. In this work, we show that the choice of IC gating function induces explicit time-dependent gradient scaling, which interacts with spectral representations during.