Consider the following class of learning schemes: $$\hat{\boldsymbol{\beta}}
:= \arg\min_{\boldsymbol{\beta}}\;\sum_{j=1}^n
\ell(\boldsymbol{x}_j^\top\boldsymbol{\beta}; y_j) + \lambda
R(\boldsymbol{\beta}),\qquad\qquad (1) $$ where $\boldsymbol{x}_i \in
\mathbb{R}^p$ and $y_i \in \mat