StochasticAD is an experimental, research package for automatic differentiation (AD) of stochastic programs. It implements AD algorithms for handling programs that can contain discrete randomness, based on the methodology developed in this NeurIPS 2022 paper. We're still working on docs and code cleanup!
The package is not yet registered, but can be installed with the repo link:
julia> using Pkg;
julia> Pkg.add(url="https://github.com/gaurav-arya/StochasticAD.jl");