DynamicHMC 2.0 was just released. I wrote a blog post about the changes and the new features. There are breaking API changes, please read the documentation . Feel free to ask support questions here.

@Tamas_Papp thanks a lot for the updated version of your package! I am a newbie in this field of MCMC for Bayesian estimation… I hope you don’t mind if I use this thread for a bit of help in understanding why my code is not working. I have quite a complicated loglikelihood function, written in Jul…

Is there a print statement somewhere in your log likelihood function?

@jkbest2 there are no `print’ statements in the loglikelihood… From what I understand by looking at the stacktrace it seems something related to internal functions of the library

My knowledge in Bayesian is really rusty and I plan to pick it up in the near future. My old textbooks all use BUGS, I recently bought the Statistical Rethinking book but it uses R. The Julian codes for this book in github seem still in progress, many chapters are missing. Do you have any recommend…

I am happy to help you with this, but I need an MWE. [image] Please read: make it easier to help you Meta Discussion Welcome to the Julia Discourse! We are enthusiastic about helping Julia programmers, both beginner and experienced. This public service announcement (PSA) …

[image] Yifan_Liu: Do you have any recommended readings for using your DynamicHMC package? Yes, there is a bibliography in the README. I would recommend starting with Bayesian Data Analysis. But Statistical Rethinking should also be fine — coding everything is part of the learning process. N…

Thanks, today I will try to strip down the loglikelihood function to the minimum that still produces the problem!

Thanks. It would be best if you opened an issue on Github, with version information etc. BTW, are you sure you are using 2.0.0 or master? There was an issue like this which was fixed by this line . Your line numbers in the stacktrace don’t match up with the current version, but that could be an unre…

Hey thanks a lot, I was not using the last version I think. I have now updated to Julia 1.2 and I got the packages from your github repository and now everything works. Incidentally for some reason I still get the same problem if I run the code in Jupyter notebook instead of in a script…

Thanks. I will read these materials.

ANN: DynamicHMC 2.0

Package Announcements

Tamas_Papp September 5, 2019, 7:06am 6

I am happy to help you with this, but I need an MWE.

Topic		Replies	Views
Custom likelihoods in Turing.jl General Usage	15	3914	October 26, 2018
MCMC landscape Statistics question	99	14618	July 2, 2021
DynamicHMC API rewrite Statistics question	1	769	July 25, 2019
A community convention for target function return values General Usage statistics , optimization , machine-learning	12	1281	July 1, 2020
DynamicHMC: multivariate normal loglikelihood? General Usage	10	1089	May 24, 2019

ANN: DynamicHMC 2.0

Related topics