Conditioning one block of a jointly Gaussian vector on another gives a Gaussian law with linear mean and Schur-complement covariance.
For a zero-mean Gaussian process observed with independent Gaussian noise, the latent value at a new input is conditionally normal. Its mean is the kernel cross-covariance times the noisy kernel-matrix inverse times the observations, and its variance is the prior variance minus the corresponding quadratic form.
Articles by others on the same topic
There are currently no matching articles.