Samuel Brand

Incompatibility with Flux.jl

1

Hi there, There is some compatibility drift on this package, which now means it can't be installed with Flux. Which is a bit of a problem!

Progress reporting in parallel sampling

3

Hi everyone, One thing I've noticed is that progress reporting when doing chains in parallel (for example using `MCMCThreads()`) is not informative, the progress meter only updates when a chain...

Problem with using `predict` with vector valued random variables

18

Hi everyone, ## Problem There seems to be a problem with using `predict` in conjunction with models that use vectorisation. Consider this fairly simple example: ```math \begin{split} \sigma \sim \text{HalfNormal}(0.1)...

Using Dagger in an epidemiological analysis: visualising an implied DAG and other examples of usage

10

Hi everyone, I'm implementing an analysis batch for an epidemiological modelling package https://github.com/CDCgov/Rt-without-renewal/tree/main/pipeline . We're wondering if there is a functionality for graph plotting a DAG after it has been...

As of recently (julia 1.10.3 release?) the build of `GR_jll` can't find `LERC` anymore among the julia artefacts. This means it can't compile and therefore `Plots.jl` is unusable as a...

Safety for poisson random calls

6

Hi everyone, Base Julia can't convert large floats into `Int` type using `floor` or `round` etc. This creates a problem for sampling from Poisson's with a large mean because this...

Stress test utility for numpyro?

2

Hi everyone, I'm working on an ODE based model (solver from diffrax) for respiratory viruses fitted on past seasons of data. At the moment, we occasionally have maximum iteration fails...

I've noticed on a project that myself and @seabbs are benchmarking with `BenchmarkCI` https://github.com/CDCgov/Rt-without-renewal/tree/main/benchmark that I can't add `OrdinaryDiffEq` because of incompatibility between `SetField` version used here and the compat...