plotSymDevFun: Display the Symmetric Deviation Function

In mbinois/GPareto: Gaussian Processes for Pareto Front Estimation and Optimization

Display the Symmetric Deviation Function

Description

Display the Symmetric Deviation Function for an object of class CPF.

Usage

plotSymDevFun(CPF, n.grid = 100)

Arguments

CPF	CPF object, see CPF,
n.grid	number of divisions of the grid in each dimension.

Details

Display observations in red and the corresponding Pareto front by a step-line. The blue line is the estimation of the location of the Pareto front of the kriging models, named Vorob'ev expectation. In grayscale is the intensity of the deviation (symmetrical difference) from the Vorob'ev expectation for couples of conditional simulations.

References

M. Binois, D. Ginsbourger and O. Roustant (2015), Quantifying Uncertainty on Pareto Fronts with Gaussian process conditional simulations, European Journal of Operational Research, 243(2), 386-394.

Examples

library(DiceDesign)
set.seed(42)

nvar <- 2

# Test function
fname = "P1"

# Initial design
nappr <- 10
design.grid <- maximinESE_LHS(lhsDesign(nappr, nvar, seed = 42)$design)$design
response.grid <- t(apply(design.grid, 1, fname))

ParetoFront <- t(nondominated_points(t(response.grid)))

# kriging models : matern5_2 covariance structure, linear trend, no nugget effect
mf1 <- km(~., design = design.grid, response = response.grid[, 1])
mf2 <- km(~., design = design.grid, response = response.grid[, 2])

# Conditional simulations generation with random sampling points 
nsim <- 10 # increase for better results
npointssim <- 80 # increase for better results
Simu_f1 = matrix(0, nrow = nsim, ncol = npointssim)
Simu_f2 = matrix(0, nrow = nsim, ncol = npointssim)
design.sim = array(0,dim = c(npointssim, nvar, nsim))

for(i in 1:nsim){
  design.sim[,, i] <- matrix(runif(nvar*npointssim), npointssim, nvar)
  Simu_f1[i,] = simulate(mf1, nsim = 1, newdata = design.sim[,, i], cond = TRUE,
                         checkNames = FALSE, nugget.sim = 10^-8)
  Simu_f2[i,] = simulate(mf2, nsim = 1, newdata = design.sim[,, i], cond=TRUE, 
                         checkNames = FALSE, nugget.sim = 10^-8)
}

# Attainment, Voreb'ev expectation and deviation estimation
CPF1 <- CPF(Simu_f1, Simu_f2, response.grid, ParetoFront)

# Symmetric deviation function
plotSymDevFun(CPF1)

mbinois/GPareto documentation built on Feb. 1, 2024, 4:35 a.m.