Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the adversarial loss with most hypothesis sets is NP-hard.

Specifically,our main idea istolearn the sharing pattern through atask-specific policy that selectively chooses which layers to execute for a given task in the multi-task network.

The whole is greater than its parts and the parts constitute the whole.

The sliding window model of computation captures scenarios in which data is arriving continuously,butonly thelatestwelements should beused foranalysis.

Noisy labels are inevitable in large real-world datasets.