Add init_params keyword argument

src/abstractmcmc.jl

@@ -19,10 +19,10 @@ end
 
 # first step of the elliptical slice sampler
 function AbstractMCMC.step(
-    rng::Random.AbstractRNG, model::AbstractMCMC.AbstractModel, ::ESS; kwargs...
+    rng::Random.AbstractRNG, model::AbstractMCMC.AbstractModel, ::ESS; init_params=nothing, kwargs...
 )
     # initial sample from the Gaussian prior
-    f = initial_sample(rng, model)
+    f = init_params === nothing ? initial_sample(rng, model) : init_params
 
     # compute log-likelihood of the initial sample
     loglikelihood = Distributions.loglikelihood(model, f)

test/simple.jl

@@ -41,6 +41,7 @@
 
         # model
         prior = Normal(0.5, 1)
+        init_x = randn()
 
         # true posterior
         μ = 0.9
@@ -62,13 +63,18 @@
             @test mean(mean, samples) ≈ μ atol = 0.05
             @test mean(var, samples) ≈ σ² atol = 0.05
         end
+
+        # initial parameter
+        sample = sample(ESSModel(prior, ℓ), ESS(), 10; progress=false, init_params=init_x)
+        @test first(samples) == init_x
     end
 
     @testset "Scalar model (vectorized)" begin
         Random.seed!(1)
 
         # model
         prior = MvNormal([0.0], I)
+        init_x = randn(1)
 
         # true posterior
         μ = [0.8]
@@ -91,6 +97,10 @@
             @test mean(mean, samples) ≈ μ atol = 0.05
             @test mean(var, samples) ≈ σ² atol = 0.05
         end
+
+        # initial parameter
+        sample = sample(ESSModel(prior, ℓ), ESS(), 10; progress=false, init_params=init_x)
+        @test first(samples) == init_x
     end
 
     @testset "Scalar model with nonzero mean (vectorized)" begin