Trying to sample my Gaussian Process with MCMC

Hello I am using GuassianProcessess.jl, I have been looking at their tutorial (Simple GP Regression · GaussianProcesses.jl) and implement it. Likewise, I want to implement a kernel with summing its value. Now I would like run a chain to optimize the hyper parameters. But I am running into this error, can anybody help me?

using Random

# Training data
n=10;                          #number of training points
x = 2π * rand(n);              #predictors
y = sin.(x) + 0.05*randn(n); 

#Select mean and covariance function
#here values are log scaled. 
mZero = MeanZero()                   #Zero mean function
kern1 = Periodic(log(1.0), log(1.0), log(1.5))        #Sqaured exponential kernel (note that hyperparameters are on the log scale)
kern2 = Noise(log(0.01))
kern = kern1+kern2               # log standard deviation of observation noise (this is optional)
gp = GP(x,y,mZero,kern, 0) 

μ, σ² = predict_y(gp,range(0,stop=2π,length=100));


Try replacing 0 with 0.0 in all locations in your code

1 Like