Skip to yearly menu bar Skip to main content


Poster

Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms

Elvis Dohmatob · Meyer Scetbon

Hall C 4-9 #2201
[ ] [ Paper PDF ]
Thu 25 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

In this paper, we investigate the impact of test-time adversarial attacks on linear regression models and determine the optimal level of robustness that any model can reach while maintaining a given level of standard predictive performance (accuracy). Through quantitative estimates, we uncover fundamental tradeoffs between adversarial robustness and accuracy in different regimes. We obtain a precise characterization which distinguishes between regimes where robustness is achievable without hurting standard accuracy and regimes where a tradeoff might be unavoidable. Our findings are empirically confirmed with simple experiments that represent a variety of settings. This work covers feature covariance matrices and attack norms of any nature, extending previous works in this area.

Chat is not available.