Risk minimization by median-of-means tournaments (Q2302852)

This paper develops an approach for squared error minimization based on a median of means estimator and pairwise comparisons of candidate functions. Optimality in terms of accuracy and confidence is discussed in different scenarios, determined in terms of classes of estimation functions and hypotheses on the tails of the distributions. Comparisons with the approach based on empirical risk minimization are performed. Examples of application to linear regression are presented.