Gaussian Processes from First Principles

Documentation for package ‘gaussianprocesses’ version 1.0.0

Help Pages

-- B --

basis_mean	Parametric mean functions
benchmark_exact_gp_scaling	Benchmark exact-GP scaling
benchmark_sparse_gp	Benchmark sparse FITC against exact GP regression
bernoulli_likelihood	Likelihoods for Gaussian-process models

-- C --

changepoint_kernel	Changepoint kernels
coef.gaussianprocesses_latent_model	Coefficients of a Gaussian-process mean
coef.gaussianprocesses_model	Coefficients of a Gaussian-process mean
coefficient_prior	Treatments of mean-function coefficients
compare_gp_predictions	Compare two GP posterior predictions numerically
constant_mean	Gaussian-process mean functions

-- E --

estimate_coefficients	Treatments of mean-function coefficients
evaluate_kernel	Evaluate a kernel specification
evaluate_likelihood	Evaluate a likelihood and its derivatives
evaluate_mean	Evaluate a Gaussian-process mean function

-- F --

fitted.gaussianprocesses_heteroscedastic_model	Base R methods for fitted Gaussian-process models
fitted.gaussianprocesses_latent_model	Base R methods for fitted Gaussian-process models
fitted.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
fitted.gaussianprocesses_sparse_model	Base R methods for fitted Gaussian-process models
fitted.gaussianprocesses_state_space_model	Base R methods for fitted Gaussian-process models
fit_gp	Fit an exact Gaussian-process regression model
fit_heteroscedastic_gp	Fit an approximate heteroscedastic Gaussian process
fit_latent_gp	Fit a latent Gaussian-process model
fit_sparse_gp	Fit a sparse Gaussian process (FITC or VFE)
fit_time_series_gp	Fit a GP to ordered time-series observations
forecast_gp	Forecast or interpolate from a time-aware GP model
forecast_metrics	Uncertainty-aware forecast metrics

-- G --

gaussianprocesses_heteroscedastic_model	Fitted model objects
gaussianprocesses_latent_model	Fitted model objects
gaussianprocesses_model	Fitted model objects
gaussianprocesses_sparse_model	Fitted model objects
gaussianprocesses_state_space_model	Fitted model objects
gaussian_likelihood	Likelihoods for Gaussian-process models
gp_calibration_diagnostics	Summarize Gaussian-process uncertainty calibration
gp_classification_scores	Scores of binary probability forecasts
gp_coefficients	Coefficients of a Gaussian-process mean
gp_count_scores	Scores of count forecasts
gp_diagnostics	Comprehensive diagnostics for an exact Gaussian-process model
gp_holdout_scores	Proper scoring rules for Gaussian predictions
gp_hyperparameter_uncertainty	Uncertainty of estimated hyperparameters
gp_likelihoods	Likelihoods for Gaussian-process models
gp_loo_scores	Proper scoring rules for Gaussian predictions
gp_mean_functions	Gaussian-process mean functions
gp_model_methods	Base R methods for fitted Gaussian-process models
gp_numerical_diagnostics	Summarize numerical conditioning of a fitted GP
gp_profile_likelihood	Profile likelihood of one hyperparameter
gp_scores	Proper scoring rules for Gaussian predictions
gp_simulation_scenario	Generate standard GP simulation scenarios
gp_time_index	Build an explicit Gaussian-process time index

-- I --

initialize_spectral_mixture

Initialise a spectral-mixture kernel from the data's spectrum

-- K --

kernel_diagonal	Evaluate only the diagonal of a kernel matrix
kernel_gradient	Derivatives of a covariance matrix with respect to log hyperparameters
kernel_input_gradient	Derivatives of a covariance matrix with respect to the inputs
kernel_linear	Linear covariance kernel
kernel_matern	Matérn covariance kernels
kernel_matern12	Matérn covariance kernels
kernel_matern32	Matérn covariance kernels
kernel_matern52	Matérn covariance kernels
kernel_parameters	Extract kernel parameters
kernel_periodic	Periodic covariance kernel
kernel_rational_quadratic	Rational-quadratic covariance kernel
kernel_rbf	Squared-exponential covariance kernel
kernel_white_noise	White-noise covariance kernel

-- L --

likelihood_predictive	Predictive distribution of new responses
linear_kernel	Create a linear kernel specification
linear_mean	Parametric mean functions
logLik.gaussianprocesses_heteroscedastic_model	Base R methods for fitted Gaussian-process models
logLik.gaussianprocesses_latent_model	Base R methods for fitted Gaussian-process models
logLik.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
logLik.gaussianprocesses_sparse_model	Base R methods for fitted Gaussian-process models
logLik.gaussianprocesses_state_space_model	Base R methods for fitted Gaussian-process models
log_marginal_likelihood	Gaussian-process log marginal likelihood
log_marginal_likelihood_gradient	Gradient of the Gaussian-process log marginal likelihood
loo_gp	Exact leave-one-out Gaussian-process diagnostics

-- M --

matern12_kernel	Create Matérn kernel specifications
matern32_kernel	Create Matérn kernel specifications
matern52_kernel	Create Matérn kernel specifications
matern_kernel_specs	Create Matérn kernel specifications
mean_coefficients	Treatments of mean-function coefficients

-- N --

nobs.gaussianprocesses_heteroscedastic_model	Base R methods for fitted Gaussian-process models
nobs.gaussianprocesses_latent_model	Base R methods for fitted Gaussian-process models
nobs.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
nobs.gaussianprocesses_sparse_model	Base R methods for fitted Gaussian-process models
nobs.gaussianprocesses_state_space_model	Base R methods for fitted Gaussian-process models

-- O --

optimize_gp	Optimize Gaussian-process hyperparameters
optimize_latent_gp	Optimize the hyperparameters of a latent Gaussian-process model
optimize_sparse_gp	Optimize the hyperparameters of a sparse Gaussian process
optimize_time_series_gp	Optimize the hyperparameters of a time-series GP

-- P --

parametric_means	Parametric mean functions
periodic_kernel	Create a periodic kernel specification
poisson_likelihood	Likelihoods for Gaussian-process models
polynomial_mean	Parametric mean functions
predict.gaussianprocesses_heteroscedastic_model	Base R methods for fitted Gaussian-process models
predict.gaussianprocesses_latent_model	Base R methods for fitted Gaussian-process models
predict.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
predict.gaussianprocesses_sparse_model	Base R methods for fitted Gaussian-process models
predict.gaussianprocesses_state_space_model	Base R methods for fitted Gaussian-process models
predict_gp	Predict from an exact Gaussian-process regression model
predict_gradient_gp	Predict the gradient of the latent function
predict_heteroscedastic_gp	Predict from an approximate heteroscedastic GP
predict_latent_gp	Predict from a latent Gaussian-process model
predict_sparse_gp	Predict from a sparse Gaussian-process model
print.summary.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
product_kernel	Multiply covariance kernels

-- R --

rational_quadratic_kernel	Create a rational-quadratic kernel specification
rbf_kernel	Create an RBF kernel specification
residuals.gaussianprocesses_heteroscedastic_model	Base R methods for fitted Gaussian-process models
residuals.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
residuals.gaussianprocesses_sparse_model	Base R methods for fitted Gaussian-process models
residuals.gaussianprocesses_state_space_model	Base R methods for fitted Gaussian-process models
rolling_origin_gp	Rolling-origin evaluation for time-aware Gaussian processes
run_gp_benchmark_suite	Run the standard GP benchmark suite

-- S --

sample_gp_posterior	Draw functions from a Gaussian-process posterior
sample_gp_posterior.default	Draw functions from a Gaussian-process posterior
sample_gp_posterior.gaussianprocesses_heteroscedastic_model	Draw functions from a Gaussian-process posterior
sample_gp_posterior.gaussianprocesses_latent_model	Draw functions from a Gaussian-process posterior
sample_gp_posterior.gaussianprocesses_model	Draw functions from a Gaussian-process posterior
sample_gp_posterior.gaussianprocesses_sparse_model	Draw functions from a Gaussian-process posterior
sample_gp_posterior.gaussianprocesses_state_space_model	Draw functions from a Gaussian-process posterior
sample_gp_prior	Draw functions from a Gaussian-process prior
scale_kernel	Scale a covariance kernel
select_dimensions	Restrict a kernel to selected input columns
select_inducing_points	Select inducing points deterministically
simulate_gp_data	Simulate observations from a Gaussian process
spectral_mixture_kernel	Spectral-mixture kernels
summary.gaussianprocesses_heteroscedastic_model	Base R methods for fitted Gaussian-process models
summary.gaussianprocesses_latent_model	Base R methods for fitted Gaussian-process models
summary.gaussianprocesses_model	Base R methods for fitted Gaussian-process models
summary.gaussianprocesses_sparse_model	Base R methods for fitted Gaussian-process models
summary.gaussianprocesses_state_space_model	Base R methods for fitted Gaussian-process models
sum_kernel	Add covariance kernels

-- T --

time_series_kernel

Create a trend-periodic-local time-series kernel

-- U --

update_kernel_parameters

Update parameters in a kernel specification

-- V --

vcov.gaussianprocesses_model

Coefficients of a Gaussian-process mean

-- W --

white_noise_kernel

Create a white-noise kernel specification

-- Z --

zero_mean

Gaussian-process mean functions