Real-world-robustness of tree-based classifiers
share
The concept of trustworthy AI has gained widespread attention lately. One of the aspects relevant to trustworthy AI is robustness of ML models. In this study, we show how to compute the recently introduced measure of real-world-robustness - a measure for robustness against naturally occurring distortions of input data - for tree-based classifiers. The original method for computing real-world-robustness works for all black box classifiers, but is only an approximation. Here we show how real-world-robustness, under the assumption that the natural distortions are given by multivariate normal distributions, can be exactly computed for tree-based classifiers.
READ FULL TEXT