Solution

ID: past-exam-of-the-mathematics-course-of-the-university-of-cambridge/2025/iii/paper-219/3/a/solution

Put and retain , which equals one for the stated exponential covariance function. The covariance matrix of is
Conditioning a multivariate normal distribution and simplifying gives
The absence of from both conditional moments shows that and are conditionally independent given . Equivalently, the exponential-kernel Gaussian process is the stationary Ornstein-Uhlenbeck process, which is Markov.

New to topics? Read the docs here!