Hi, I would like to know why I keep getting very weird initial evaluation results even though I set the initval as 1 for all my prior distributions. with pm.Model() as model: a1 = pm.HalfNormal('a1', sigma=10, initval=1) a2 = pm.HalfNormal('a2', sigma=10, initval=1) a3 = pm.Half…

Specifically, you can use the init argument to pm.sample() to select one of several difference initialization strategies (list is here ).

Unexpected Initial evaluation results

Questions v5

Hyung June 29, 2022, 8:23pm 4

Thank you for this solution – so far, with advi init option, it solved the issue. Now I am trying to figure out why jitter+diag option caused the problem. Thank you so much!

Topic		Replies	Views
Initial values not being used when sampling v5	7	2094	July 15, 2022
SamplingError: Initial evaluation of model at starting point failed! Questions modeling , sampling	6	1010	December 8, 2022
Pymc SamplingError: Initial evaluation of model at starting point failed! Questions	2	3512	June 19, 2021
Error with Model: Initial evaluation of model at starting point failed! Questions	5	13439	August 1, 2023
Pymc problem: SamplingError: Initial evaluation of model at starting point failed! Questions	1	1013	January 12, 2022

Unexpected Initial evaluation results

Related topics