Hi. Is there a way to resume sampling from a previous trace / inference data (or other state from a previous sampling run)? I’d like to be able to draw more samples, without having to draw any tuning samples. I’m using the NUTS sampler and I’ve tried the approach @junpenglao outlines in this discus…

Resuming sampling from a previous trace

michaelosthege May 17, 2023, 8:23pm 10

@juststarted I didn’t have the time (I have other priorities), but I am not aware of problems either. The test_mcbackend.py suite runs with every CI in the PyMC project, for example.

Topic		Replies	Views
Saving the state of the sampler in pymc3? Questions	11	1579	August 20, 2020
Pause and resume training a model that can change during training Questions	2	1438	May 2, 2019
Reuse tuning for next sampling call Questions	9	2249	February 8, 2019
Pause and resume sampling while changing the model v5	5	721	March 10, 2023
Restarting sampling from stored multitrace: mixed sampling and tuning Questions	2	586	October 5, 2020

Resuming sampling from a previous trace

Related topics