We derive a fundamental trade-off between standard and adversarial risk in a rather general situation that formalizes the following simple intuition: "If no (nearly) optimal predictor is smooth, adversarial robustness comes at the cost of accuracy." As a concrete example, we evaluate the derived trade-off in regression with polynomial ridge functions under mild regularity conditions. Generalizing our analysis of this example, we formulate a necessary condition under which adversarial robustness can be achieved without significant degradation of the accuracy. This necessary condition is expressed in terms of a quantity that resembles the Poincar\'{e} constant of the data distribution.
@article{arxiv.2411.05853,
title = {A Fundamental Accuracy--Robustness Trade-off in Regression and Classification},
author = {Sohail Bahmani},
journal= {arXiv preprint arXiv:2411.05853},
year = {2025}
}