Number Theoretic Accelerated Learning of Physics-Informed Neural Networks
This addresses computational efficiency for researchers and practitioners using PINNs to solve partial differential equations, though it appears incremental as it builds on existing number theoretic methods.
The paper tackles the problem of accelerating physics-informed neural networks (PINNs) by reducing discretization errors through better collocation point selection, achieving 2-7 times fewer points required while maintaining competitive performance.
Physics-informed neural networks solve partial differential equations by training neural networks. Since this method approximates infinite-dimensional PDE solutions with finite collocation points, minimizing discretization errors by selecting suitable points is essential for accelerating the learning process. Inspired by number theoretic methods for numerical analysis, we introduce good lattice training and periodization tricks, which ensure the conditions required by the theory. Our experiments demonstrate that GLT requires 2-7 times fewer collocation points, resulting in lower computational cost, while achieving competitive performance compared to typical sampling methods.