LGMLFeb 11, 2020

Generalised Lipschitz Regularisation Equals Distributional Robustness

arXiv:2002.04197v126 citations
AI Analysis

This provides a foundational theoretical framework connecting adversarial robustness and distributional robustness, applicable to exotic function classes like universal approximators.

The paper establishes a theoretical equivalence between generalized Lipschitz regularization and distributional robustness with transportation cost uncertainty sets, enabling tight robustness certification for Lipschitz-regularized models under mild assumptions.

The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximators. In response, we give a very general equality result regarding the relationship between distributional robustness and regularisation, as defined with a transportation cost uncertainty set. The theory allows us to (tightly) certify the robustness properties of a Lipschitz-regularised model with very mild assumptions. As a theoretical application we show a new result explicating the connection between adversarial learning and distributional robustness. We then give new results for how to achieve Lipschitz regularisation of kernel classifiers, which are demonstrated experimentally.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes