Based on the description in Run Stan's MCMC algorithms — model-method-sample • cmdstanr this doesn’t seem possible, but it would be a required feature when saving the warmed up parameters from multiple chains. By contrast, it’s straightforward to pass different step sizes for each chain.

It accepts a metric per chain, just not documented as having that capability. You just do inv_metric = warmup$inv_metric(matrix=F). Here’s the full warmup-then-sample code: warmup = mod$sample( data = data_for_stan , chains = parallel_chains , parallel_chains = parallel_chains , refresh = 0 ,…

Noice! I won’t always be expecting this, but I love how quickly folks have been responding. Maybe we’re all working on the same problem, rn.

@jonah and @rok_cesnovar , the documentation for cmdstanr should be adjusted.

Yeah, been working on the composed warmup+sampling since last week (inc the bug I alerted you to in another thread). Ben Bales just now worked out why that bug was happening .

Thanks @charlesm93 and @mike-lawrence . will make an issue to fix doc.

Passing a different mass matrix for each chain in cmdstanr

Interfaces

mike-lawrence January 13, 2021, 10:27pm 8

FYI the bug was worked out, and I also posted some code that achieves things properly.

Topic		Replies	Views
Saved mass matrix General	22	2905	December 12, 2022
Sampling chains from the middle in cmdstanpy General	10	565	October 8, 2020
Lame version of shared warmup via threading General	7	489	October 15, 2020
Extracting step size per chain in cmdstanr Interfaces	7	1070	January 13, 2021
Resume sampling after interuption Interfaces cmdstanpy	5	1404	May 12, 2020

Passing a different mass matrix for each chain in cmdstanr

Related topics