Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection

ArXi:2603.23318v1 Announce Type: new Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction. However, its applicability is limited than some of its alternatives, since it requires the use of generative models and restricts the analyses either to specific model architectures or discrete features.