Compute and prepare the sgl call arguments for the objective function $$\mathrm{loss}(\mathrm{data})(\beta) + \lambda \left( (1-\alpha) \sum_{J=1}^m \gamma_J \|\beta^{(J)}\|_2 + \alpha \sum_{i=1}^{n} \xi_i |\beta_i| \right)$$ where \(\mathrm{loss}\) is a loss/objective function. The \(n\) parameters are organized in the parameter matrix \(\beta\) with dimension \(q\times p\). The vector \(\beta^{(J)}\) denotes the \(J\) parameter group, the dimension of \(\beta^{(J)}\) is denote by \(d_J\). The dimensions \(d_J\) must be multiple of \(q\), and \(\beta = (\beta^{(1)} \cdots \beta^{(m)})\). The group weights \(\gamma \in [0,\infty)^m\) and the parameter weights \(\xi \in [0,\infty)^{qp}\).
prepare.args(data, ...)a data object
additional parameters
a vector of length \(m\), containing the dimensions \(d_J\) of the groups (i.e. the number of parameters in the groups)
a vector of length \(m\), containing the group weights
a matrix of dimension \(q \times p\), containing the parameter weights
the \(\alpha\) value
the data parsed to the loss module
original order of the columns of \(\beta\). Before sgl routines return \(\beta\) will be reorganized according to this order.
prepare.args.sgldata
Other sgldata: add_data.sgldata,
create.sgldata,
prepare.args.sgldata,
prepare_data,
rearrange.sgldata,
subsample.sgldata