Learning subgaussian classes : Upper and minimax bounds
From MaRDI portal
Abstract: We obtain sharp oracle inequalities for the empirical risk minimization procedure in the regression model under the assumption that the target Y and the model F are subgaussian. The bound we obtain is sharp in the minimax sense if F is convex. Moreover, under mild assumptions on F, the error rate of ERM remains optimal even if the procedure is allowed to perform with constant probability. A part of our analysis is a new proof of minimax results for the gaussian regression model.
This page was built for publication: Learning subgaussian classes : Upper and minimax bounds
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6242081)
