mixup and mixmatch added

[Zach-ER]

Notes:

1. Only dense losses will work with mixup.
2. Potential further performance gains to be made from storing one data_dict in the iteration_message so only one new batch is sampled per iteration.

Status

*READY/

Description

Implements https://openreview.net/pdf?id=rkBBChjiG .

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• My code follows the code style of this project.
• I have added tests to cover my changes.
• All new and existing tests passed.

Todos

• Tests
• Documentation