Configuring optimization hyper-params in Perturber

[mzweilin]

What does this PR do?

This PR enables configuring perturbation-wise hyper-params in attack optimization, such as learning rate, momentum, etc.

The main changes include

• Add support to **optim_params in Perturber.
• Adversary can fetch parameters and their optimization hyper-params by calling Perturber.parameter_groups().

Type of change

Please check all relevant options.

• [ ] Improvement (non-breaking)
• [ ] Bug fix (non-breaking)
• [x] New feature (non-breaking)
• [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
• [ ] This change requires a documentation update

Testing

Please describe the tests that you ran to verify your changes. Consider listing any relevant details of your test configuration.

• [ ] Test A
• [ ] Test B

Before submitting

• [x] The title is self-explanatory and the description concisely explains the PR
• [x] My PR does only one thing, instead of bundling different changes together
• [ ] I list all the breaking changes introduced by this pull request
• [x] I have commented my code
• [ ] I have added tests that prove my fix is effective or that my feature works
• [x] New and existing unit tests pass locally with my changes
• [x] I have run pre-commit hooks with pre-commit run -a command without errors

Did you have fun?

Make sure you had fun coding 🙃

[dxoigmn]

Is this not already supported via per-parameter options? See: https://pytorch.org/docs/stable/optim.html#per-parameter-options

[mzweilin]

Is this not already supported via per-parameter options? See: https://pytorch.org/docs/stable/optim.html#per-parameter-options

Yes, it's supported. And this PR is trying to use this feature by constructing trainable parameters with optimization information.