pGPx (version 0.1.4)

max_distance_measure: Minimize the distance in measure criterion

Description

Optimizes the distance in measure criterion.

Usage

max_distance_measure(
  lower,
  upper,
  optimcontrol = NULL,
  batchsize,
  integration.param,
  T,
  model
)

Value

A list containing

• par a matrix batchsize*d containing the optimal points

• value if optimcontrol$optim.option!=1 and optimcontrol$method=="genoud" (default options) a vector of length batchsize containing the optimum at each step otherwise the value of the criterion at the optimum.

Arguments

lower

a \(d\) dimensional vector containing the lower bounds for the optimization

upper

a \(d\) dimensional vector containing the upper bounds for the optimization

optimcontrol

the parameters for the optimization, see max_sur_parallel for more details.

batchsize

number of simulations points to find

integration.param

the parameters for the integration of the criterion, see max_sur_parallel for more details.

T

threshold value

model

a km model

References

Azzimonti D. F., Bect J., Chevalier C. and Ginsbourger D. (2016). Quantifying uncertainties on excursion sets under a Gaussian random field prior. SIAM/ASA Journal on Uncertainty Quantification, 4(1):850–874.

Azzimonti, D. (2016). Contributions to Bayesian set estimation relying on random field priors. PhD thesis, University of Bern.