We construct robust source networks by performing adversarialtraining[21,45]. Baseline refers to the misclassification rate of unperturbed images. The adversarial perturbations are subject to an` constraint of16/255, and are optimized with the TMDI-FGSMalgorithm.

Dynamic programming methods have been shown to scale much better because they exploit the tree structure by solving subtrees as independent subproblems.

They also illustrate the use of some recent advances in the theory of nonlinearempiricalprocesses.

In these cases, protected attributes can be "imputed" [

Our main contribution is an optimization framework to learn fair classifiers in this adversarial setting that comes with provable guarantees on accuracy and fairness.