prox

Return the value of the proximal operator of the nuclear norm (scaled by
<code>threshold</code>) applied to a matrix

Fit multinomial logistic regression with a penalty on the nuclear
norm of the estimated regression coefficient matrix, using proximal
gradient descent.

Scott Powers

npmr

Nuclear Penalized Multinomial Regression

prox function

<dl> <dt>B</dt>
<dd>matrix</dd> <dt>threshold</dt>
<dd>scaling factor applied to the nuclear norm. In proximal gradient descent for
NPMR, this is the product of the stepsize and the regularization parameter
lambda</dd> <dt>group</dt>
<dd>Vector of length equal to number of variables, i.e. nrow(B).
 Variables in the same group indexed by a POSITIVE integer will be penalized
 together (the nuclear norm of the sub-matrix of the regression coefficients
 will be penalized). Variables without positive integers will NOT be
 penalized. Default is NULL, which means there are no sub-groups; nuclear
 norm of entire coefficient matrix is penalized.</dd></dl>

Arguments

Scott Powers, Trevor Hastie, Rob Tibshirani

Author

Proximal operator for nuclear norm — prox

<dl>

 <dt>B</dt>
<dd>matrix</dd>

 <dt>threshold</dt>
<dd>scaling factor applied to the nuclear norm. In proximal gradient descent for
NPMR, this is the product of the stepsize and the regularization parameter
lambda</dd>

 <dt>group</dt>
<dd>Vector of length equal to number of variables, i.e. nrow(B).
 Variables in the same group indexed by a POSITIVE integer will be penalized
 together (the nuclear norm of the sub-matrix of the regression coefficients
 will be penalized). Variables without positive integers will NOT be
 penalized. Default is NULL, which means there are no sub-groups; nuclear
 norm of entire coefficient matrix is penalized.</dd>

</dl>

prox: Proximal operator for nuclear norm

Description

Usage

Value

Arguments

Author

References

See Also