simulated_annealing_method_options {WpProj}

Options For Use With the Simulated Annealing Selection Method

Description

Options For Use With the Simulated Annealing Selection Method

Usage

simulated_annealing_method_options(
  force = NULL,
  method = c("binary program", "projection"),
  transport.method = transport_options(),
  OTmaxit = 100L,
  epsilon = 0.05,
  maxit = 1L,
  temps = 1000L,
  max.time = 3600,
  proposal.method = c("covariance", "uniform"),
  energy.distribution = c("boltzman", "bose-einstein"),
  cooling.schedule = c("Geman-Geman", "exponential"),
  model.size = NULL,
  display.progress = FALSE,
  parallel = NULL,
  calc.theta = TRUE,
  ...
)

Arguments

force

Any covariates to force into the model? Should be by column number or NULL if no variables to force into the model.

method

Should covariates be selected as an approximate "binary program" or should a projection method be used. Default is the approximate binary program.

transport.method

Method for Wasserstein distance calculation. Should be one the outputs of transport_options()

OTmaxit

The number of iterations to run the Wasserstein distance solvers.

epsilon

A value > 0 for the penalty parameter of if using the Sinkhorn method for optimal transport

maxit

Maximum number of iterations per temperature

temps

Number of temperatures to try

max.time

Maximum time in seconds to run the algorithm

proposal.method

The method to propose the next covariate to add. One of "covariance" or "random". "covariance" will randomly select from covariates with probability proportional to the absolute value of the covariance. "uniform" will select covariates uniformly at random.

energy.distribution

The energy distribution to use for evaluating proposals. One of "boltzman" or "bose-einstein". Default is "boltzman".

cooling.schedule

The schedule to use for cooling temperatures. One of "Geman-Geman" or "exponential". Default is "Geman-Geman".

model.size

How many coefficients should the maximum final model have?

display.progress

Logical. Should intermediate progress be displayed? TRUE or FALSE. Default is FALSE.

parallel

A cluster backend to be used by foreach::foreach(). See foreach::foreach() for details about how to set them up. The WpProj functions will register the cluster with the doParallel::registerDoParallel() function internally.

calc.theta

Return the linear coefficients? Default is TRUE.

...

Not used.

Value

A named list with the above arguments

Examples

simulated_annealing_method_options()