I'm interested in the ground for making conditional independence assumption (e.g. that different target dimensions do not covary for given input $x$) when we are modelling some multidimensional signal with Gaussian Process? Why it is natural to assume this? Or it is just our way to manage with the curse of dimensionality?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.