Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions

Despite the popularity of Empirical Risk Minimization (ERM) algorithms, a theory that explains their statistical properties in modern high-dimensional regimes is only recently emerging. We characterize for the first time the fundamental limits on the statistical accuracy of convex ridge-regularized ERM for inference in high-dimensional generalized linear models. For a stylized setting with Gaussian features and problem dimensions that grow large at a proportional rate, we start with sharp performance characterizations and then derive tight lower bounds on the estimation and prediction error. Our bounds provably hold over a wide class of loss functions, and, for any value of the regularization parameter and of the sampling ratio. Our precise analysis has several attributes. First, it leads to a recipe for optimally tuning the loss function and the regularization parameter. Second, it allows to precisely quantify the sub-optimality of popular heuristic choices, such as optimally-tuned least-squares. Third, we use the bounds to precisely assess the merits of ridge-regularization as a function of the sampling ratio. Our bounds are expressed in terms of the Fisher Information of random variables that are simple functions of the data distribution, thus making ties to corresponding bounds in classical statistics.