Comparing stochastic derivatives to derivatives from traditional AD

gaurav-arya / StochasticAD.jl

Research package for automatic differentiation of programs containing discrete randomness.

MIT License

195 stars 15 forks source link

Comparing stochastic derivatives to derivatives from traditional AD #86

Closed frankschae closed 11 months ago

frankschae commented 1 year ago

Should we add a StochasticAD.new_Δs_strategy that resembles ForwardDiff? This would be helpful to compare e.g., the smoothing results to ForwardDiff, even when StochasticAD is loaded.