Using separate optimizers for the encoder and decoder of the TVAE

[HarrisonWilde]

Environment details

If you are already running CTGAN, please indicate the following details about the environment in which you are running it:

• CTGAN version: 0.7.1
• Python version: 3.10.11
• Operating System: MacOS

Problem description

I am interested in using the TVAE implementation in this package for a research project, I would like to be able to have separate optimizers for the decoder and encoder. I am not super familiar with VAE's (more so with GAN's), would anyone be able to help me in changing the TVAE code such that I can use one optimizer for each part, instead of one for both?

Thanks!