Learning from MOM’s principles : Le Cam’s approach

We obtain estimation error rates for estimators obtained by aggregation of regularized median-of-means tests, following a construction of Le Cam. The results hold with exponentially large probability, under only weak moments assumptions on data. Any norm may be used for regularization. When it has some sparsity inducing power we recover sparse rates of convergence. The procedure is robust since a large part of data may be corrupted, these outliers have nothing to do with the oracle we want to reconstruct. Our general risk bound is of order max ( minimax rate in the i.i.d. setup, number of outliers number of observations ) . In particular, the number of outliers may be as large as (number of data) ×(minimax rate) without affecting this rate. The other data do not have to be identically distributed but should only have equivalent L and L moments. For example, the minimax rate s log(ed/s)/N of recovery of a s-sparse vector in R is achieved with exponentially large probability by a median-of-means version of the LASSO when the noise has q0 moments for some q0 > 2, the entries of the design matrix should have C0 log(ed) moments and the dataset can be corrupted up to C1s log(ed/s) outliers.