Robustness Implies Generalization via Data-Dependent Generalization Bounds

arXiv2206.13497MaRDI QIDQ6403304FDOQ6403304

Authors: Kenji Kawaguchi, Zhun Deng, Kyle J. Luh, Jiaoyang Huang 

Publication date: 27 June 2022

Abstract: This paper proves that robustness implies generalization via data-dependent generalization bounds. As a result, robustness and generalization are shown to be connected closely in a data-dependent manner. Our bounds improve previous bounds in two directions, to solve an open problem that has seen little development since 2010. The first is to reduce the dependence on the covering number. The second is to remove the dependence on the hypothesis space. We present several examples, including ones for lasso and deep learning, in which our bounds are provably preferable. The experiments on real-world data and theoretical models demonstrate near-exponential improvements in various situations. To achieve these improvements, we do not require additional assumptions on the unknown distribution; instead, we only incorporate an observable and computable property of the training samples. A key technical innovation is an improved concentration bound for multinomial random variables that is of independent interest beyond robustness and generalization.

This page was built for publication: Robustness Implies Generalization via Data-Dependent Generalization Bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6403304)