2 papers
cs.LG2026
Auxiliary Finite-Difference Residual-Gradient Regularization for PINNs
Stavros Kassinos
Physics-informed neural networks (PINNs) are often selected by a single scalar loss even when the quantity of interest is more specific. We study a hybrid design in which the gover…
cs.LG2025
Kourkoutas-Beta: A Sunspike-Driven Adam Optimizer with Desert Flair
Stavros C. Kassinos
Transformer neural networks are increasingly used for physics-based problems. In data-driven PDE surrogates, training samples from varying boundary and initial conditions can cause…