It begins with a boundary: A geometric view on probabilistically robust learning

Author name not available (Why is that?)

Publication date: 30 May 2023

Abstract: Although deep neural networks have achieved super-human performance on many classification tasks, they often exhibit a worrying lack of robustness towards adversarially generated examples. Thus, considerable effort has been invested into reformulating Empirical Risk Minimization (ERM) into an adversarially robust framework. Recently, attention has shifted towards approaches which interpolate between the robustness offered by adversarial training and the higher clean accuracy and faster training times of ERM. In this paper, we take a fresh and geometric view on one such method -- Probabilistically Robust Learning (PRL) (Robey et al., ICML, 2022). We propose a geometric framework for understanding PRL, which allows us to identify a subtle flaw in its original formulation and to introduce a family of probabilistic nonlocal perimeter functionals to address this. We prove existence of solutions using novel relaxation methods and study properties as well as local limits of the introduced perimeters.

Has companion code repository: https://github.com/danielmckenzie/begins_with_a_boundary

This page was built for publication: It begins with a boundary: A geometric view on probabilistically robust learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6438450)