Estimates from Gaussian Process regression (function: `fitgpr`) for given set of hyperparameter

I am interested in estimating y using Gaussian Process for given hyperparameters and noise parameter i.e. without optimizing for parameters.

In the following example; [3.5, 6.2, 0.2] are provided as initial guess parameters,

load(fullfile(matlabroot,'examples','stats','gprdata2.mat'))
sigma0 = 0.2;
kparams0 = [3.5, 6.2];
gprMdl2 = fitrgp(x,y,'KernelFunction','squaredexponential',...
     'KernelParameters',kparams0,'Sigma',sigma0);
ypred2 = resubPredict(gprMdl2);

But I am interested in seeing model's response y and other properties (like: loglikelihood) precisely for parameters [3.5, 6.2, 0.2] not for optimized ones.

Thanks

Answer 1

[Gautam Pendse]

Hi Pankaj,

You probably want to use 'FitMethod','none' in the call to fitrgp. For more info, have a look at the doc for 'FitMethod':

https://www.mathworks.com/help/stats/fitrgp.html#namevaluepairarguments

Hope this helps,

Gautam