Learn R Programming

hetGP (version 1.1.7)

Heteroskedastic Gaussian Process Modeling and Design under Replication

Description

Performs Gaussian process regression with heteroskedastic noise following the model by Binois, M., Gramacy, R., Ludkovski, M. (2016) , with implementation details in Binois, M. & Gramacy, R. B. (2021) . The input dependent noise is modeled as another Gaussian process. Replicated observations are encouraged as they yield computational savings. Sequential design procedures based on the integrated mean square prediction error and lookahead heuristics are provided, and notably fast update functions when adding new observations.

Copy Link

Version

Install

install.packages('hetGP')

Monthly Downloads

581

Version

1.1.7

License

LGPL

Maintainer

Mickael Binois

Last Published

September 4th, 2024

Functions in hetGP (1.1.7)

Criterion optimization

Correlation function of selected type, supporting both isotropic and product forms

Integrated Contour Uncertainty criterion

Maximum Contour Uncertainty criterion

Contour Stepwise Uncertainty Reduction criterion

Expected Improvement criterion

Logarithm of Expected Improvement criterion

Parallel Expected improvement

Sequential IMSPE criterion

Maximum Empirical Error criterion

t-MSE criterion

Noisy 1d test function (1) Add Gaussian noise with variance r(x) = scale * (1.1 + sin(2 pi x))^2 to f1d

deriv_crit_IMSPE

Derivative of crit_IMSPE

1d test function (1)

1d test function (2)

Noisy 1d test function (2) Add Gaussian noise with variance r(x) = scale * (exp(sin(2 pi x)))^2 to f1d2

Derivative of EI criterion for GP models

Data preprocessing

Generic Log-likelihood function This function can be used to compute loglikelihood for homGP/hetGP models

Gaussian process modeling with correlated noise

Student-t process modeling with heteroskedastic noise

Gaussian process predictions using a GP object for correlated noise (of class CRNGP)

Gaussian process modeling with homoskedastic noise

Student-t process predictions using a heterogeneous noise TP object (of class hetTP)

Student-T process modeling with homoskedastic noise

pred_noisy_input

Gaussian process prediction prediction at a noisy input x, with centered Gaussian noise of variance sigma_x. Several options are available, with different efficiency/accuracy tradeoffs.

Gaussian process modeling with heteroskedastic noise

Gaussian process predictions using a heterogeneous noise GP object (of class hetGP)

Conditional simulation for CRNGP

Fast homTP-update

Gaussian process predictions using a homoskedastic noise GP object (of class homGP)

Fast conditional simulation for a CRNGP model

Fast homGP-update

Update "hetGP"-class model fit with new observations

Score and RMSE function To asses the performance of the prediction, this function computes the root mean squared error and proper score function (also known as negative log-probability density).

Student-t process predictions using a homoskedastic noise GP object (of class homGP)

Update "hetTP"-class model fit with new observations

Likelihood-based comparison of models

Compute double integral of the covariance kernel over a [0,1]^d domain

SIR test problem

Import and export of hetGP objects

Leave one out predictions

Allocation of replicates on existing designs

Integrated Mean Square Prediction Error

IMSPE optimization

Assemble To Order (ATO) Data and Fits

Bayes Factor Data