Part I.  krisp toolbox

Table of Contents

CorrVectorData — Calculates correlation between data point x and other data points, that were used for learning of kriging model.
EGO — Creates EGO optimizer.
EGO_ask — Ask optimizer for next data point.
EGO_best — Returns the best known point and corresponding criterion value.
EGO_stop — Ask optimizer if stopping criterion has been met.
EGO_tell — Tell EGO optimizer new data point and criterion value.
EI — Calculates (one point) Expected improvement.
EstimateVar — Calculates process variance and noise for kriging model.
LL_driver_optim — Returns negative log Likelihood for kriging model as a function of kriging parameters for linking with new optimization packages.
LOOCV — Calculates Leave One Out Cross-validation for given kriging model.
RLHS — Creates RLH sampling of maxiter points for n dimensions in the interval [lob,upb].
SimCondGaussian — Creates conditional gaussian process simulations.
createCorr — Creates correlation matrix R.
decompose_estBeta — Preforms Cholesky decomposition for covariance/correlation matrix. Calculates T_kriging M_kriging Ty_kriging frf_kriging Tyfb_kriging and estimates Beta_kriging if necessary.
findTheta — Optimizes over kriging hyper-parameters (corelation scale parameters (theta) and/or process variance (sigma) or proporionality coefficent between process variance and noise (alfa)), by minimizing negative Likelihood or minimizing Leave One Out Cross validation.
km — Creates kriging model, based on given parameters. It may estimate some parameters analytically.
logLL — Calculates negative log Likelihood.
poly0 — Constant trend function.
poly1 — Linear trend function.
poly2 — Quadratic trend function.
predict — Calculates predicted kriging mean and variance at points x;
rescale — Rescales X.
showModel — Displays information about kriging model.
simGaussian — Creates Gaussian process simulations based on given covariance and mean information.