create_inits: Create a list with initial values.

In cbdavis33/bcgp: Bayesian Composite Gaussian Processes

Description

create_inits returns a list that contains initial values randomly generated from the prior distribution.

Usage

create_inits(x, composite, stationary, noise, priors, chains)

Arguments

x	An n x d matrix containing the independent variables in the training set.
priors	A list that contains the parameter values for the priors.
chains	The number of Markov chains. The default is 4.

Details

This creates a list of length chains that contains randomly generated initial values. The intention is to specify initial values for the parameters for the Markov chains. The user can change the values as they like prior to inputting the list into bcgp.

Value

A list of length chains The elements of this list will be named lists, where each of these has the name of a parameter.

TODO

Decide whether to add options for "heteroscedastic" and "composite"

See Also

bcgp

Examples

x <- matrix(runif(40), ncol= 4, nrow = 10)
create_inits(x)
create_inits(x, priors = create_priors(), chains = 2)

cbdavis33/bcgp documentation built on Oct. 1, 2019, 8:07 a.m.