Evolutionary Two-Stage Hyperparameter Optimization Strategies for Physics-Informed Neural Networks
For practitioners using PINNs, this method addresses the sensitivity to hyperparameters and unstable convergence, offering a more robust and efficient way to improve solution accuracy.
The paper proposes a two-stage evolutionary hyperparameter optimization strategy for Physics-Informed Neural Networks (PINNs) that first screens configurations with low-fidelity training and then refines the best candidates, achieving significantly lower mean error on Advection, Klein-Gordon, and Helmholtz equations under constrained computational budgets.
Physics-Informed Neural Networks (PINNs) solve Partial Differential Equations (PDEs) by embedding physical laws into neural network training. However, their performance suffers from unstable convergence, training plateaus, and strong sensitivity to architectural and optimization hyperparameters due to the highly non-convex and multi-term structure of the physics-informed loss. In this setting, the outer-loop hyperparameter search is a noisy and black-box optimization problem over heterogeneous parameters, where classical local or gradient-based strategies are easily trapped in suboptimal regions. Evolutionary algorithms, with their population-based exploration and ability to handle mixed, non-differentiable search spaces, provide a more robust mechanism for discovering promising configurations. We propose and investigate a two-stage approach based on evolutionary algorithms that combines exploration and exploitation parts of PINNs training to improve solution accuracy and robustness under fixed computational budgets. In the first stage, we perform low-fidelity training runs with truncated epochs to rapidly screen candidate configurations, treating hyperparameter selection as a black-box outer-loop problem. In the second stage, only the most promising candidates are fully trained with standard gradient-based optimizers to refine the solution. Evaluated on three popular problems, namely Advection, Klein-Gordon and Helmholtz equations, our method consistently outperforms standard training and achieves significantly lower mean error within constrained computational resources.