A Fundamental Accuracy--Robustness Trade-off in Regression and Classification

TMLR Paper3620 Authors

Abstract:

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.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Han_Bao2

Submission Number: 3620