Major internet companies routinely perform tensofthousands ofA/Btests each year.

To improve the learnability of deep learning models, various techniques have been proposed.

Isitpossibleto acquire therequired domain expertise, without involving human experts?

In this work, we demonstrate that these two seemingly orthogonal concepts are remarkably well-suited for each other.

TheobjectiveofGANs istoproduce random samples from atarget data distribution, given only access toan initial set of training samples. This isachievedbylearning twofunctions: ageneratorG,which maps random input noise to a generated sample, and a discriminatorD, which tries to classify input samples as either real (i.e., from the training dataset) or fake (i.e., produced by the generator).