A method for importance sampling through Markov chain Monte Carlo with post sampling variational estimate

摘要

We propose a method to efficiently integrate truncated probability densities.The method uses Markov chain Monte Carlo method to sample from a probabilitydensity matching the function being integrated. The required normalisation orequivalently the result is obtained by constructing a function with knownintegral, through non-parametric kernel density estimation and variationalprocedure. The method is demonstrated with numerical case studies. Possibleenhancements to the method and limitations are discussed.