fitrgp function: problem with custom kernel

Hi all,

I am trying to train a Gaussian Process model with the function fitrgp, using a custom kernel. A matrix dimension problem appears when computing, and I'm not able to resolve it.

I reproduce the ARD-squared exponential kernel for the example:

This is my code:

if true
  kernel = @(xp,xq,theta) theta(8).^2 * exp(-1/2 * sum( ...
                             ((xp(1, 1:(length(theta)-1)) - xq(1, 1:(length(theta)-1))) .^2) ...
                              ./ (theta(1, 1:(length(theta)-1)) .^2)));

   theta0 = [5, 2000, 20, 10, 40, 0.5, 0.5, 0.1];

   GP_model = fitrgp(training_table,'CELLS_Delta_Q_shft_large', 'Basis','none','KernelFunction',kernel,'KernelParameters',theta0,...
                          'FitMethod','exact','PredictMethod','exact');

end

'training_table' is a 910x8 table, and 'CELLS_Delta_Q_shft_large' is the name of the last column.

The error specifies:

if true
Index exceeds matrix dimensions.

Error in
@(xp,xq,theta)theta(8).^2*exp(-1/2*sum(((xp(1,1:(length(theta)-1))-xq(1,1:(length(theta)-1))).^2)./(theta(1,1:(length(theta)-1)).^2)))

Error in classreg.learning.gputils.CustomKernel/makeKernelAsFunctionOfTheta/f (line 138)
              KNM = customFcn(XN,XM,theta);

Error in classreg.learning.impl.GPImpl/makeNegativeProfiledLogLikelihoodExact/f1 (line 970)
              [V,DK]       = kfcn(theta);

Error in classreg.learning.gputils.fminqn (line 199)
                      f     = fun(x);

Error in classreg.learning.impl.GPImpl/doMinimization (line 3007)
                      [phiHat,fHat,~,exitFlag] = classreg.learning.gputils.fminqn(objFun,phi0,'Options',opts);

Error in classreg.learning.impl.GPImpl/estimateThetaHatSigmaHatExact (line 855)
              [phiHat,nloglikHat,cause] = doMinimization(this,objFun,phi0,haveGrad);

Error in classreg.learning.impl.GPImpl/doFitMethodExact (line 422)
          [this.ThetaHat,this.SigmaHat,this.LogLikelihoodHat] =
          estimateThetaHatSigmaHatExact(this,this.X,this.y,this.Beta0,this.Theta0,this.Sigma0);

Error in classreg.learning.impl.GPImpl/doFit (line 362)
                  this = doFitMethodExact(this);

Error in classreg.learning.impl.GPImpl.make (line 264)
          this = doFit(this);

Error in RegressionGP (line 277)
          this.Impl = classreg.learning.impl.GPImpl.make(...

Error in classreg.learning.FitTemplate/fit (line 258)
          [varargout{1:nargout}] = this.MakeFitObject(X,Y,W,this.ModelParams,fitArgs{:});

Error in RegressionGP.fit (line 305)
          this = fit(temp,X,Y);

Error in fitrgp (line 493)
  obj = RegressionGP.fit(X,Y,RemainingArgs{:});
end

Do you have any idea about what I'm doing wrong?

Thank you