I have timeseries data that I’d like to model with pm.sample_smc() by first getting the posterior given the data at timepoint 1, then pass that posterior as inits for a next run that has data for timepoints 1-3, then repeat until the model has “seen” all the data. Does anyone have any existing code …

Examples for SMC with streaming data?

cluhmann December 12, 2023, 4:20am 13

PyMC’s find_contrainted_prior() function is somewhat related.

Topic		Replies	Views
Using MCMC based model in closed loop Questions	14	2525	July 29, 2019
Using the starts argument to sample_smc() v5	1	272	November 2, 2023
Simulating new data points while having data-dependent priors Questions	0	453	May 10, 2019
SMC sampling appears to not allow supplying a starting trace Development	3	800	June 26, 2018
Sample from prior? Questions	9	3525	July 20, 2018