Hi, is there a (preferably simple) way to implement multi-output gaussian processes in pymc? As for “additional” features I think I need “non-centered cross-covariance” (i.e. different outputs being related with a small time delay) and “negative cross-covariance” (i.e. different outputs related in …

Multi-output gaussian processes

bwengals October 8, 2017, 12:50am 5

Yep, @junpenglao is right. Also check out this thread.

Topic		Replies	Views
New to Gaussian Processes question on single output and multiple inputs gaussian_process , modeling	3	559	June 17, 2023
Modeling Gaussian process from multiple function observations? Questions	1	878	March 14, 2018
Need for a review of my GP tutorial Sharing	11	1349	April 4, 2022
Develop multi-output GP model with linear mean for each task and with learnable hyperparameters v5	6	833	April 17, 2023
Multiple (uncertain) function observations of the same Gaussian process Questions	15	6404	October 16, 2017