Inverse classification with logistic and softmax classifiers: efficient optimization

ArXi:2309.08945v2 Announce Type: replace In recent years, a certain type of problems have become of interest where one wants to query a trained classifier. Specifically, one wants to find the closest instance to a given input instance such that the classifier's predicted label is changed in a desired way. Examples of these "inverse classification" problems are counterfactual explanations, adversarial examples and model inversion.