# laGP v1.5-5

0

0th

Percentile

## Local Approximate Gaussian Process Regression

Performs approximate GP regression for large computer experiments and spatial datasets. The approximation is based on finding small local designs for prediction (independently) at particular inputs. OpenMP and SNOW parallelization are supported for prediction over a vast out-of-sample testing set; GPU acceleration is also supported for an important subroutine. OpenMP and GPU features may require special compilation. An interface to lower-level (full) GP inference and prediction is provided. Wrapper routines for blackbox optimization under mixed equality and inequality constraints via an augmented Lagrangian scheme, and for large scale computer model calibration, are also provided.

## Functions in laGP

 Name Description darg Generate Priors for GP correlation discrep.est Estimate Discrepancy in Calibration Model llikGP Calculate a GP log likelihood fcalib Objective function for performing large scale computer model calibration via optimization distance Calculate the squared Euclidean distance between pairs of points laGP Localized Approximate GP Prediction At a Single Input Location deleteGP Delete C-side Gaussian Process Objects blhs Bootstrapped block Latin hypercube subsampling aGP Localized Approximate GP Regression For Many Predictive Locations alcGP Improvement statistics for sequential or local design randLine Generate two-dimensional random paths newGP Create A New GP Object mleGP Inference for GP correlation parameters optim.auglag Optimize an objective function under multiple blackbox constraints predGP GP Prediction/Kriging No Results!