I’m experiencing what seems to be the same problem as highlighted in various other posts ( #1983 , #1083 , #1304 ), although none of the proposed solutions have worked for my model. I am running a Gaussian Process Regression in a for loop where for each iteration in the loop my target ‘y’ variable chan…

Broadcasting problem with Metropolis Sampling

junpenglao July 27, 2019, 7:39pm 3

But you really shouldnt be using Metropolis especially with GP - it is a high dimensional problem and MH most likely give you bias or even wrong result

Topic		Replies	Views
Larger dataset linear regression GPU memory problems with NUTS for larger N and D (batch training?) Questions theano	2	1868	October 3, 2017
Shape of posterior predictive samples of GP Questions	3	555	November 10, 2019
Multidimensional gaussian process Questions	55	10240	October 22, 2020
Gaussian Process Regression with hyperpriors Questions	6	2039	August 28, 2019
Mixed multivariate Gauss distribution Questions	39	4948	April 12, 2018

Broadcasting problem with Metropolis Sampling

Related topics