2-Wasserstein distance selection by Integer Programming
W2IP(
X,
Y = NULL,
theta,
transport.method = transport_options(),
model.size = NULL,
nvars = NULL,
maxit = 100L,
infimum.maxit = 100L,
tol = 1e-07,
solver = c("cone", "lp", "mosek", "cplex", "gurobi"),
display.progress = FALSE,
parallel = NULL,
...
)
Covariates
Predictions from arbitrary model
Parameters of original linear model. Required
Method for Wasserstein distance calculation. Should be one of the outputs of transport_options()
.
Maximum number of coefficients in interpretable model
The number of variables to explore. Should be an integer vector of model sizes. Default is NULL which will explore all models from 1 to model.size
.
Maximum number of solver iterations
Maximum iterations to alternate binary program and Wasserstein distance calculation
Tolerance for convergence of coefficients
The solver to use. Must be one of "cone","lp", "cplex", "gurobi","mosek".
Should progress be printed?
foreach back end. See foreach::foreach()
for more details.
Extra args to Wasserstein distance methods
For argument solution.method
, options "cone" and "lp" use the free solvers "ECOS" and "lpSolver", respectively. "cplex", "gurobi" and "mosek" require installing the corresponding commercial solvers.