Hello, I have a model where I need to optimize N independent Gaussian processes and would like to have a way to batch them using PyMC3’s GP API. N is usually less than 10, so not massive. I basically need a way to specify K_i(x, x') = \sigma^2 \exp \left[ -\frac{(x_i-x_i')^2}{2l_i^2} \right] w…

Batched Gaussian Processes

junpenglao January 22, 2019, 5:59am 2

Have you look into using MatrixNormal or KroneckerNormal?

Topic		Replies	Views
Multiple (uncertain) function observations of the same Gaussian process Questions	15	6568	October 16, 2017
Modeling Gaussian process from multiple function observations? Questions	1	896	March 14, 2018
Extending Gaussian Process functionality: Coregion and beyond Development	19	2390	November 25, 2017
Multi-output gaussian processes Questions	13	5511	October 22, 2017
Multidimensional input using Gaussian Process Questions	6	4028	June 28, 2017