I am trying to get access to the LOO and WAIC metrics for model selection as in the documentation. In my problem, the sampling consumes about 500 MB during the sampling process which seems quite reasonable to me. However, once i call pymc.compute_log_likelihood(trace), the RAM usage jumps to ove…

Compute_log_likelihood RAM usage is huge

dans September 26, 2023, 10:21pm 2

Does anyone have any pointers on this? Is this function expected to eat up so much RAM?
Is there another way of going about this?

Topic		Replies	Views
Memory spike at the end of the MCMC sampling Questions	10	2681	July 15, 2022
Unexpected Results when using WAIC to Compute Log Predictive Accuracy Questions	3	688	May 13, 2018
Sampling draw time increases massively near "finish line" for 1M observed rows Questions	3	439	July 28, 2021
Outputting loglikelihood of each parameter set Questions	10	685	March 22, 2022
Understand root cause of high memory utilization v3	8	724	December 8, 2023