FriesischScott/UncertaintyQuantification.jl

Subset-∞

FriesischScott opened this issue · 1 comments

The algorithm generates the conditional samples for the next level by representing each random variable by an arbitrary number of hidden variables instead of using Markov Chain Monte Carlo.

Reference: Patelli & AU (2015) Efficient Monte Carlo algorithm for rare failure event simulation

If we extract the generation of next level samples into a separate method, this should be easy to implement.