PointEstimator: PointEstimator

In NeuralEstimators: Likelihood-Free Parameter Estimation using Neural Networks

PointEstimator

Description

Construct a neural Bayes point estimator. The neural-network architecture is still defined in Julia (e.g. via juliaEval()); this function wraps that architecture in a PointEstimator.

Typical constructors, matching the Julia methods:

• PointEstimator(network): a single network mapping data to the parameter space.

• PointEstimator(num_parameters, summary_network, num_summaries = ...): a summary network with an MLP inference network built internally.

Usage

PointEstimator(...)

Arguments

...	arguments passed to the Julia version of PointEstimator()

Value

a PointEstimator

See Also

PosteriorEstimator(), RatioEstimator(), train(), infer()

Examples

## Not run: 
library("NeuralEstimators")
library("JuliaConnectoR")
juliaEval("using NeuralEstimators, Flux")
network <- juliaEval("
  n = 1; d = 2; w = 32
  psi = Chain(Dense(n, w, relu), Dense(w, w, relu))
  phi = Chain(Dense(w, w, relu), Dense(w, d))
  DeepSet(psi, phi)
")
estimator <- PointEstimator(network)

## End(Not run)

NeuralEstimators documentation built on Sept. 10, 2026, 1:12 a.m.