On the Variance, Admissibility, and Stability of Empirical Risk Minimization

It is well known that Empirical Risk Minimization (ERM) with squared loss may attain minimax suboptimal error rates (Birg\'e and Massart, 1993). The key message of this paper is that, under mild assumptions, the suboptimality of ERM must be due to large bias rather than variance. More precisely, in the bias-variance decomposition of the squared error of the ERM, the variance term necessarily enjoys the minimax rate. In the case of fixed design, we provide an elementary proof of this fact using the probabilistic method. Then, we prove this result for various models in the random design setting. In addition, we provide a simple proof of Chatterjee's admissibility theorem (Chatterjee, 2014, Theorem 1.4), which states that ERM cannot be ruled out as an optimal method, in the fixed design setting, and extend this result to the random design setting. We also show that our estimates imply stability of ERM, complementing the main result of Caponnetto and Rakhlin (2006) for non-Donsker classes. Finally, we show that for non-Donsker classes, there are functions close to the ERM, yet far from being almost-minimizers of the empirical loss, highlighting the somewhat irregular nature of the loss landscape.