Explore different function approximators for the complex phase of the wavefunction

[rgmelko]

Can we replace the second RBM with some other neural network function approximator

[Roger-luo]

I think this is a great idea. I had a tomography framework (in private, a draft) for GAN based tomography with pytorch last year (GAN is failed on the tomography though...). I could share the prototype code and write some proposal for this.

[Roger-luo]

Here is some of my legacy code for QST & VMC for reference:

Pure python implementation:

https://github.com/Roger-luo/legacy-QMTK

With C++ optimized:

https://github.com/Roger-luo/legacy-QMTK/tree/cpp

Some functionalities in the package was separated to other projects in QuantumBFS and re-write in Julia (work in progress).