Collocation-based Robust Variational Physics-Informed Neural Networks (CRVPINN)
This work addresses a computational bottleneck for researchers using VPINNs to solve PDEs, offering an incremental improvement in training efficiency.
The paper tackles the slow convergence of Robust Variational Physics-Informed Neural Networks (RVPINNs) by introducing CRVPINN, which uses a LU factorization of sparse Gram matrices in a point-collocation scheme, achieving up to 10x faster training times on Laplace, advection-diffusion, and Stokes problems in 2D.
Physics-Informed Neural Networks (PINNs) have been successfully applied to solve Partial Differential Equations (PDEs). Their loss function is founded on a strong residual minimization scheme. Variational Physics-Informed Neural Networks (VPINNs) are their natural extension to weak variational settings. In this context, the recent work of Robust Variational Physics-Informed Neural Networks (RVPINNs) highlights the importance of conveniently translating the norms of the underlying continuum-level spaces to the discrete level. Otherwise, VPINNs might become unrobust, implying that residual minimization might be highly uncorrelated with a desired minimization of the error in the energy norm. However, applying this robustness to VPINNs typically entails dealing with the inverse of a Gram matrix, usually producing slow convergence speeds during training. In this work, we accelerate the implementation of RVPINN, establishing a LU factorization of sparse Gram matrix in a kind of point-collocation scheme with the same spirit as original PINNs. We call out method the Collocation-based Robust Variational Physics Informed Neural Networks (CRVPINN). We test our efficient CRVPINN algorithm on Laplace, advection-diffusion, and Stokes problems in two spatial dimensions.