Probing optimisation in physics-informed neural networks
A novel comparison is presented of the effect of optimiser choice on the accuracy of physics-informed neural networks (PINNs). To give insight into why some optimisers are better, a new approach is proposed that tracks the training trajectory curvature and can be evaluated on the fly at a low computational cost. The linear advection equation is studied for several advective velocities, and we show that the optimiser choice substantially impacts PINNs model performance and accuracy. Furthermore, using the curvature measure, we found a negative correlation between the convergence error and the curvature in the optimiser local reference frame. It is concluded that, in this case, larger local curvature values result in better solutions. Consequently, optimisation of PINNs is made more difficult as minima are in highly curved regions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
An Analysis of Physics-Informed Neural Networks
Whilst the partial differential equations that govern the dynamics of our world have been studied in great depth for centuries, solving them for complex, high-dimensional conditions and domains still presents an incredib…
Seismic ImagingAn Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks
Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solvers. The obstacle is increasingly unders…
Physics-Informed Neural Networks for Solving Derivative-Constrained PDEs
Physics-Informed Neural Networks (PINNs) recast PDE solving as an optimisation problem in function space by minimising a residual-based objective, yet many applications require additional derivative-based relations that …
Scaling physics-informed neural networks to large domains by using domain decomposition
Recently, physics-informed neural networks (PINNs) have offered a powerful new paradigm for solving forward and inverse problems relating to differential equations. Whilst promising, a key limitation to date is that PINN…
jinns: a JAX Library for Physics-Informed Neural Networks
jinns is an open-source Python library for physics-informed neural networks, built to tackle both forward and inverse problems, as well as meta-model learning. Rooted in the JAX ecosystem, it provides a versatile framewo…