muscor.model {muscor}R Documentation

Create a muscor model.

Description

Create a muscor model. To be used for muscor().

Usage

muscor.model (coefficients=NULL,
             loss.type=c("Least.Squares","Logistic.Regression",
                                 "Modified.LS","Modified.Huber"),
             lambda.ridge=0, lambda.sparse=0,
             sparse.type=c("capped.L1","Lp"),
             sparse.param=0,
             intercept=FALSE)

Arguments

coefficients The computed coefficients. If intercept=TRUE, it has d+1 components, with the last component being the intercept parameter. Otherwise, it has d components. Default is NULL.
loss.type One of "Least.Squares","Logistic.Regression", "Modified.LS","Modified.Huber". The names can be abbreviated to any unique substring. Least.Squares is for regression with real-valued y. The other loss functions are for binary classification, assuming y to be {+1,-1} valued, and described in [Tong Zhang (2004)]. Default is "Least.Squares".
lambda.ridge Ridge (L2) regularization parameter. Default is zero.
lambda.sparse Sparse regularization parameter: it can be a vector of size "stages" to specific different regularization strength for different stages. Default is zero.
sparse.type One of "capped.L1" or "Lp". Default is "capped.L1".
sparse.param If sparse.type="Lp", R(w)=|w|_p^p, and sparse.param is the p in (0,1]. If sparse.type=capped.L1, R(w)=sum_j max(|w_j|,g); sparse.param=g if it has positive value, and g is choen such as no more than |sparse.param| number of |w| is larger than g if it has value <= 0. Default is 0.
intercept If TRUE, an intercept is included in the model (and not penalized); otherwise no intercept is included. Default is FALSE.

Details

The Multi-stage Convex Relaxation approach is described in [Tong Zhang (2008)]. It relaxes the non-convex problem into L1 regularization problems in stages, and each L1 regularization problem is solved using the function opt.L1().

Value

A muscor model is returned. It is a list containing the same components as the arguments.

Author(s)

Tong Zhang

References

Tong Zhang (2004) "Statistical Behavior and Consistency of Classification Methods based on Convex Risk Minimization", Annals of Statistics, 32:56–85, 2004.

Tong Zhang (2008) "Multi-stage Convex Relaxation for Learning with Sparse Regularization", NIPS'08.

See Also

muscor predict.muscor and opt.L1


[Package muscor version 0.2 Index]