<ul><li>Selective classification is a powerful tool for automated decision-making in high-risk scenarios, allowing classifiers to make highly confident decisions while abstaining when uncertainty is high.</li><li>The goal of this study is to minimize the number of indecisions, which are observations that are not automated, while achieving a target classification accuracy.</li><li>The study provides a full characterization of the minimax risk in selective classification, proving key properties and enabling optimal indecision selection.</li><li>The findings highlight the potential of selective classification to significantly reduce misclassification rates with a relatively small cost in terms of indecisions.</li></ul>

Ask for More Than Bayes Optimal: A Theory of Indecisions for Classification

Discover more