Double-charging privacy in DC-GAN example

[ffuuugor]

tl;dr: dcgan.py example adds noise to the fake data gradients, which it doesn't need to.
We should change the training pipeline (because it's more correct) and measure the impact (because we're curious).

See more details and solution proposals on the PyTorch forum thread

[Koukyosyumei]

@ffuuugor

Hi! I'm Hideaki, an undergrad student at the University of Tokyo and a research intern at Tsinghua University on privacy-preserving machine learning. I am currently working on this issue. I've made a PR but need approval from the maintainer to run the workflow. How should I proceed?

[romovpa]

@Koukyosyumei Thank you for contributing!
We will review it soon. Let's discuss in your PR, I've left a comment.