# PG fails to sample properly with acclogp!
**URL:** https://discourse.julialang.org/t/pg-fails-to-sample-properly-with-acclogp/67924
**Category:** Probabilistic Programming
**Created:** [September 9, 2021, 10:40am UTC](https://discourse.julialang.org/t/pg-fails-to-sample-properly-with-acclogp/67924 "2021-09-09T10:40:21Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@sami1](https://discourse.julialang.org/u/sami1)
#### Post date: [September 9, 2021, 10:40am UTC](https://discourse.julialang.org/t/pg-fails-to-sample-properly-with-acclogp/67924/1 "2021-09-09T10:40:21Z")
Hello,
I’m currently trying to sample from a posterior with a mixture of differentiable and discrete parameters, some of them I can’t marginalize. I tried to marginalize the one I could using acclogp!, and sample the rest of the discrete parameters with PG.
However I realized that doing this, PG fails to sample from the posterior, and samples from the prior.
Here is an MWE :
```nohighlight
@model minimodel(Y) = begin
μ ~ Normal(0, 1)
σ ~ InverseGamma(2, 1)
Turing.acclogp!( __varinfo__ , logpdf(filldist(Normal(μ, σ), length(Y)), Y))
end
Y = 2 .+ 0.3*randn(1000)
chn = sample(minimodel(Y), PG(20), 1000)
```
returns :
```julia
Summary Statistics
parameters mean std naive_se mcse ess rhat ess_per_sec
Symbol Float64 Float64 Float64 Float64 Float64 Float64 Float64
μ -0.0106 0.9972 0.0315 0.0313 996.6409 0.9990 231.9928
σ 1.0773 2.1186 0.0670 0.0670 970.7092 0.9991 225.9565
```
By plotting the result, you can easily check that it just sampled the prior. I can go around this issue with trick in the flavour of
```nohighlight
L = logpdf(filldist(Normal(μ, σ), length(Y)), Y)
1 ~ Bernoulli(exp(L/length(Y)))
```
But I’d like to know if it’s a intended behavior, and if so what am I missing ?
Thanks
---
### Author:  [@torfjelde](https://discourse.julialang.org/u/torfjelde)
#### Post date: [September 9, 2021, 2:33pm UTC](https://discourse.julialang.org/t/pg-fails-to-sample-properly-with-acclogp/67924/2 "2021-09-09T14:33:20Z")
`PG` requires knowledge about what is considered an observation and what is not, so unfortunately it won’t be compatible with usage of `@acclogprob!` as a replacement for the observe `~` 😕
EDIT: We have ideas on introducing traits for samplers, etc., so that we can warn/error in these cases.
---
### Author:  [@sami1](https://discourse.julialang.org/u/sami1)
#### Post date: [September 9, 2021, 3:33pm UTC](https://discourse.julialang.org/t/pg-fails-to-sample-properly-with-acclogp/67924/3 "2021-09-09T15:33:49Z")
Got it ! Thanks for the quick answer