AI RESEARCH
On the Statistical Optimality of Optimal Decision Trees
arXiv CS.LG
•
ArXi:2603.05340v2 Announce Type: replace-cross While globally optimal empirical risk minimization (ERM) decision trees have become computationally feasible and empirically successful, rigorous theoretical guarantees for their statistical performance remain limited. In this work, we develop a comprehensive statistical theory for ERM trees under random design in both high-dimensional regression and classification.