ARCHISSUR (version 0.0.1)

precomputeUpdateData: Useful precomputations to quickly update GPC mean and variance

Description

Useful precomputations to quickly update GPC mean and variance

Usage

precomputeUpdateData(model, integration.points)

Value

a list with components:

c.K

Vector equal to \(t(c)K^{-1}\) where \(K^{-1}\) is the inverse covariance matrix invK returned by object and c the unconditional covariance matrix between newdata and design points Xf

lambda.intpoints

Vector equal to \(K^{-1}c\) where \(K^{-1}\) is the inverse covariance matrix invK returned by object and c the unconditional covariance matrix between newdata and design points Xf

pn.intpoints

the (averaged) probability of class 1 at integration.points.

intpoints.oldmean

conditional mean matrix of the latent GP at integration.points

intpoints.oldmean

conditional variance vector of the latent GP at integration.points

Arguments

model

an object of class gpcm.

integration.points

p*d matrix of fixed integration points in the X space.

Author

Morgane MENZ, Delphine SINOQUET, Miguel MUNOZ-ZUNIGA. Contributors: Naoual SERRAJI.

References

Menz, M., Munoz-Zuniga, M., Sinoquet, D. Estimation of simulation failure set with active learning based on Gaussian Process classifiers and random set theory (2023). https://hal.science/hal-03848238.

Bachoc, F., Helbert, C. & Picheny, V. Gaussian process optimization with failures: classification and convergence proof. J Glob Optim 78, 483–506 (2020). tools:::Rd_expr_doi("10.1007/s10898-020-00920-0").

Examples

#-------------------------------------------------------------------
#------------------- precomputeUpdateData ----------------------------
#-------------------------------------------------------------------

## 20-points DoE, and the corresponding response
d <- 2
nb_PX <- 20
x <- matrix(c(0.205293785978832, 0.0159983370750337,
              0.684774733109666, 0.125251417595962,
              0.787208786290006, 0.700475706055049,
              0.480507717105934, 0.359730889653793,
              0.543665267336735, 0.565974761807069,
              0.303412043992361, 0.471502352650857,
              0.839505250127309, 0.504914690245002,
              0.573294917143728, 0.784444726564573,
              0.291681289223421, 0.255053812451938,
              0.87233450888786, 0.947168337730927,
              0.648262257638515, 0.973264712407035,
              0.421877310273815, 0.0686662506387988,
              0.190976166753807, 0.810964668176754,
              0.918527262507395, 0.161973686467513,
              0.0188128700859558, 0.43522031347403,
              0.99902788789426, 0.655561821513544,
              0.741113863862512, 0.321050086076934,
              0.112003007565305, 0.616551317575545,
              0.383511473487687, 0.886611679106771,
              0.0749211435982952, 0.205805968972305),
            byrow = TRUE, ncol = d)
require(DiceKriging)
fx <- apply(x, 1, branin)
f <- ifelse(fx < 14, -1, 1)
Xf <- as.matrix(x)


## gpcm object
require(GPCsign)
require(randtoolbox)
model <- gpcm(f, Xf, coef.m = -1.25, coef.cov = c(1.17,0.89))

nb.integration <- d * 100
integration.points <- sobol(n = nb.integration, dim = d, scrambling = 0)
integration.points <- scale(x = integration.points, center = [e-mail], scale = [e-mail])

precalc.data <-  precomputeUpdateData(model = model, integration.points = integration.points)