transport_plan_given_C {approxOT}

Optimal transport plans given a pre-specified cost

Description

Optimal transport plans given a pre-specified cost

Usage

transport_plan_given_C(
  mass_x,
  mass_y,
  p = 2,
  cost = NULL,
  method = "exact",
  cost_a = NULL,
  cost_b = NULL,
  ...
)

Arguments

mass_x

The empirical measure of the first sample

mass_y

The empirical measure of the second sample.

p

The power of the Wasserstein distance

cost

Specify the cost matrix in advance.

method

The transportation method to use, one of "exact", "networkflow","shortsimplex", "sinkhorn", "greenkhorn"

cost_a

The cost matrix for the first sample with itself. Only used for unbiased Sinkhorn

cost_b

The cost matrix for the second sample with itself. Only used for unbiased Sinkhorn

...

Additional arguments for various methods

• "niter": The number of iterations to use for the entropically penalized optimal transport distances

• "epsilon": The multiple of the median cost to use as a penalty in the entropically penalized optimal transport distances

• "unbiased": If using Sinkhorn distances, should the distance be de-biased? (TRUE/FALSE)

Value

A transportation plan as an object of class "transport.plan", which is a list with slots "from","to", and "mass".

Examples

n <- 32
d <- 5
set.seed(293897)
A <- matrix(stats::rnorm(n*d),nrow=d,ncol=n)
B <- matrix(stats::rnorm(n*d),nrow=d,ncol=n)
transp.meth <- "sinkhorn"
niter <- 1e2
test <- transport_plan_given_C(rep(1/n,n), 
rep(1/n,n),  2, cost = cost_calc(A,B,2), 
"sinkhorn", niter = niter)