Section: New Results

Robust risk minimization for machine learning

In collaboration with S. Minsker (USC), T. Mathieu worked on obtaining new excess risk bounds in robust empirical risk minimization. The method proposed in [29] is inspired from the robust risk minimization procedure using median-of-means estimators in Lecué, Lerasle and Mathieu (2018). The obtained excess risk are faster than the so-called "slow rate of convergence" obtained for the minimization procedure in Lecué, Lerasle and Mathieu (2018) and a slightly modified procedure achieves a minimax rate of convergence under low moment assumptions. Experiments on synthetic corrupted data and real dataset illustrate the accuracy of the method showing high performance in classification and regression tasks in a corrupted setting.