-
Notifications
You must be signed in to change notification settings - Fork 2
Open
Description
Differentiating through an MCMC sampler as below is an uncommon operation.
ADTests/models/metabayesian_MH.jl
Lines 32 to 36 in ff99b21
inner_m = inner_model(observation, subj_prior_μ, subj_prior_σ) | |
# Run the inner Bayesian inference | |
chns = sample(Xoshiro(468), inner_m, inner_sampler, inner_n_samples, progress = false) | |
# Extract subjective point estimate | |
subj_mean_expectationₜ = mean(chns[:mean]) |
I don't think it is a meaningful example for AD tests since most AD backends won't have a rule for Turing.sample
. Meanwhile, automatically derived rules for Turing.sample
are meaningless for most MCMC samplers, including MH
.
Metadata
Metadata
Assignees
Labels
No labels