Physics informed neural network package for hyperparameter tuning

Question

Is there any good PINN package or algorithm for hyperparameter tuning to accelerate convergence?

Answer 1

If its specifically related to picking best hyperparameters for your PINNs model. Try libraries like Optuna combined with any of the above parameters.

One such example of using an existing PINNs framework along with Optuna can be found here.

Answer 2

Here are some PINN implementations/packages that might be useful for you:

• NVIDIA Modulus (previously: SimNet)
• DeepXDE from Lu Lu, George Em Karniadakis et al.
• JAX-PI from Sifan Wang, Paris Perdikaris et al.
• PINA from Gianluigi Rozza et al.