Hey! I was wondering if there is a way in the current PyMC version to customize the jitter used in the “jitter+[xyz]” initialization. By default it is a uniform sample from [-1,1], but could I make it e.g. choose from [-0.1,0.1]? Thanks for your insights! Cheers!

@TimOliverMaier you can pass your manually jittered initial point to sample. I think that would be the easiest? The kwarg is initvals

Change distribution of jitter

Questions v5

cluhmann July 11, 2023, 11:56am 2

I don’t believe so. If you are having issues with the default initialization (jitter+adapt_diag), you can try one of the others that is available (see here for the full list).

1 Like

Topic		Replies	Views
Initial values not being used when sampling v5	7	2094	July 15, 2022
Difference between 'jitter+adapt_diag' and 'adapt_diag'? Questions	2	1271	April 2, 2019
Initialization energy is NaN or Inf with jitter Questions	4	1338	December 9, 2020
Init progress bar gone? Questions	7	1026	February 16, 2018
Unexpected Initial evaluation results v5 modeling	6	812	June 30, 2022

Change distribution of jitter

Related topics