Chad Scherrer

Results 185 issues of Chad Scherrer

- [ ] Implement transport API for most finite measures - [ ] Drop TransformVariables dependency - [ ] Factor out `ExponentialFamily` and `Tweedie` into https://github.com/cscherrer/MeasureFamilies.jl

For push-forwards, we have ```julia pushfwd(f, m) ``` If the `f` of a pushforward is noisy, it becomes a kernel, and the pushforward becomes a compound measure: https://en.wikipedia.org/wiki/Compound_probability_distribution This is...

```julia julia> using Symbolics julia> @variables μp σp μq σq x; julia> logdensity_rel(Normal(μp,σp), Normal(μq,σq), x) |> simplify (1//2)*(((x - μq) / σq)^2) - (1//2)*(((x - μp) / σp)^2) ``` Note...

@fredrikekre 's comment [here](https://github.com/JuliaLang/Pkg.jl/issues/1585#issuecomment-578187367) says, > Don't use the functionality of `test/Project.toml`s which is pretty beta (and documented as such) But this is not clear at all from current documentation...

@mschauer mentioned in Slack that Mitosis.jl likes to work with nonlinear models that have Gaussian conditionals. With the upcoming transport API in MeasureBase.jl, we should be able to automate this...

Hi, Have you looked into updating this for Julia v0.6? It's currently not building for me. I made some syntax updates on a fork, but it quickly gets into some...

In case you haven't seen it, this is really helpful: https://github.com/abelsiqueira/Breakage It gives you results like this: https://github.com/cscherrer/KeywordCalls.jl/actions/runs/888461853 For this to be really useful, tests in downstream packages (Transits and...

I'm not sure if this is really an `Aqua` issue - it might be a bug in Julia itself. I often get results like ``` Ambiguity #1 logdensity_def(s::S, β, x)...

bug
duplicate
test: ambiguities