Hi, I’m having trouble with combining the for-loop and the CustomDist function, which worked when I used pymc.MvNormal instead of CustomDist. I’d like to seek advice on how to tackle this issue. I’m writing a custom likelihood function needed for my analysis using a linear mixed models framework. …

If you are using the latest PyMC you can try calling pymc.model.transform.optimization.freeze_dims_and_data — PyMC dev documentation and then sampling with numpyro. Otherwise you can try the nutpie sampler which uses the numba backend. Are you sure your implementations are the same? Numpyro sample…

For loop does not work for CustomDist distribution

Questions v5

ricardoV94 July 9, 2024, 5:28am 4

If you could provide a reproducible snippet for the ufunc part that would be useful for us to finally reproduce that error

Topic		Replies	Views
Declare an internal Poisson distribution inside a custom distribution failes Questions	21	2096	April 30, 2018
Trouble with Initilization and Posterior Sampling Questions theano	13	2225	June 15, 2018
Implementing Chinese Restaurant Process - pytensor error on CustomDist v5	3	362	February 5, 2024
Sampling the Banana-shaped distribution Questions	14	3872	July 24, 2018
Implementing a new distribution (loop over x and y in logp) Questions	1	559	November 2, 2018

For loop does not work for CustomDist distribution

Related topics