Add three of the DPPL models from https://arxiv.org/pdf/2002.02702

Author: penelopeysm

.github/workflows/generate_website.yml

@@ -87,6 +87,7 @@ jobs:
         run: uv run ad.py run --model ${{ matrix.model }}
         env:
           ADTYPE_KEYS: ${{ needs.setup-keys.outputs.adtype_keys }}
+          DATADEPS_ALWAYS_ACCEPT: "true"
 
       - name: Output matrix values
         id: output-matrix

Project.toml

@@ -3,13 +3,16 @@ ADTypes = "47edcb42-4c32-4615-8424-f2b9edc5f35b"
 Chairmarks = "0ca39b1e-fe0b-4e98-acfc-b1656634c4de"
 DifferentiationInterface = "a0c0ee7d-e4b9-4e03-894e-1c5f64a51d63"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
+DistributionsAD = "ced4e74d-a319-5a8a-b0ac-84af2272839c"
 DynamicPPL = "366bfd00-2699-11ea-058f-f148b4cae6d8"
 Enzyme = "7da242da-08ed-463a-9acd-ee780be4f1d9"
 FiniteDifferences = "26cc04aa-876d-5657-8c51-4c34ba976000"
 ForwardDiff = "f6369f11-7733-5829-9624-2563aa707210"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 LogDensityProblems = "6fdf6af0-433a-55f7-b3ed-c6c6e0b8df7c"
+MLDatasets = "eb30cadb-4394-5ae3-aed4-317e484a6458"
 Mooncake = "da2b9cff-9c12-43a0-ae48-6db2b0edb7d6"
+MultivariateStats = "6f286f6a-111f-5878-ab1e-185364afe411"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 ReverseDiff = "37e2e3b7-166d-5795-8a7a-e32c996b4267"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"

main.jl

@@ -35,6 +35,7 @@ end
 # These imports tend to get used a lot in models
 using DynamicPPL: @model, to_submodel
 using Distributions
+using DistributionsAD: filldist, arraydist
 using LinearAlgebra
 
 include("models/assume_beta.jl")
@@ -74,6 +75,10 @@ include("models/observe_submodel.jl")
 include("models/pdb_eight_schools_centered.jl")
 include("models/pdb_eight_schools_noncentered.jl")
 
+include("models/dppl_gauss_unknown.jl")
+include("models/dppl_high_dim_gauss.jl")
+include("models/dppl_naive_bayes.jl")
+
 # The entry point to this script itself begins here
 if ARGS == ["--list-model-keys"]
     foreach(println, sort(collect(keys(MODELS))))

models/dppl_gauss_unknown.jl

@@ -0,0 +1,12 @@
+n = 10_000
+s = abs(rand()) + 0.5
+y = randn() .+ s * randn(n)
+
+@model function dppl_gauss_unknown(y)
+    N = length(y)
+    m ~ Normal(0, 1)
+    s ~ truncated(Cauchy(0, 5); lower=0)
+    y ~ filldist(Normal(m, s), N)
+end
+
+@register dppl_gauss_unknown(y)

models/dppl_high_dim_gauss.jl

@@ -0,0 +1,5 @@
+@model function dppl_high_dim_gauss(D)
+    m ~ filldist(Normal(0, 1), D)
+end
+
+@register dppl_high_dim_gauss(10_000)

models/dppl_naive_bayes.jl

@@ -0,0 +1,27 @@
+using MLDatasets: MNIST
+using MultivariateStats: fit, PCA, transform
+
+# Load MNIST images and labels
+features = MNIST(split=:train).features
+nrows, ncols, nimages = size(features)
+image_raw = Float64.(reshape(features, (nrows * ncols, nimages)))
+labels = MNIST(split=:train).targets .+ 1
+C = 10 # Number of labels
+
+# Preprocess the images by reducing dimensionality
+D = 40
+pca = fit(PCA, image_raw; maxoutdim=D)
+image = transform(pca, image_raw)
+
+# Take only the first 1000 images and vectorise
+N = 1000
+image_subset = image[:, 1:N]'
+image_vec = vec(image_subset[:, :])
+labels = labels[1:N]
+
+@model dppl_naive_bayes(image_vec, labels, C, D) = begin
+    m ~ filldist(Normal(0, 10), C, D)
+    image_vec ~ MvNormal(vec(m[labels, :]), I)
+end
+
+@register dppl_naive_bayes(image_vec, labels, C, D)