Patrick Stiller

It's not needed. Control structures in the constructor just blow up the code base.

Implement benchmark suite with: - [ ] standard setups for various PDEs - [ ] default argument parser - [ ] switch of and on various PDEs by the argument...

- [ ] single flag for storing gradients - [ ] Outsource annealing - [ ] Outsource orthogonalisation

Currently, the fit function is a very big function that includes tracking, fitting, parallelization, etc. Here we should modularize the functionalities to get a more maintainable code.

At the moment, you need to set the number of main training epochs to 0, activate the pretaining function, and deactivate lbfgs fine-tuning. Here it would be better to have...

In the HPMLoss the weighting is not set correctly. ``` super(HPMLoss, self).__init__(dataset, None, name, norm='L2', weight=1.) ``` should be ``` super(HPMLoss, self).__init__(dataset, None, name, norm='L2', weight=weight) ```

The general idea of the framework is not well transported and should be better illustrated

Setting the default batch_size to `None` leads to a more understandable behaviour (dataloader yields a shape [n, dim])

Port the 2D Schrodinger to the framework

1

- [ ] Split the EC Dataset into three datasets - [ ] Implement the Normalization Condition as a new designed Boundary Condition (https://pytorch.org/docs/stable/generated/torch.trapz.html) could make things easier - [...