The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli

We revisit the recently introduced Local Glivenko-Cantelli setting, which studies distributiondependent uniform convergence rates of the EmpiricalMean Estimator (EME). In this work, weinvestigate generalizations of this setting where arbitrary estimators are allowed rather than just the EME. Can a strictly larger class of measures be learned? Can better risk decay rates be obtained? We provide exhaustive answers to these questions—which are both negative, provided the learner is barred from exploiting some infinitedimensional pathologies. On the other hand, allowing such exploits does lead to a strictly larger class of learnable measures.