Skip to yearly menu bar Skip to main content


Poster

Reducing Adversarially Robust Learning to Non-Robust PAC Learning

Omar Montasser · Steve Hanneke · Nati Srebro

Poster Session 5 #1547

Abstract:

We study the problem of reducing adversarially robust learning to standard PAC learning, i.e. the complexity of learning adversarially robust predictors using access to only a black-box non-robust learner. We give a reduction that can robustly learn any hypothesis class C using any non-robust learner A for C. The number of calls to A depends logarithmically on the number of allowed adversarial perturbations per example, and we give a lower bound showing this is unavoidable.

Chat is not available.