Augmented nested sampling for stochastic programs with recourse and endogenous uncertainty. (22nd January 2018)

• Record Type: Journal Article
• Authors: Ekin, Tahir; Polson, Nicholas G.; Soyer, Refik
• Is Part Of: Naval research logistics. Volume 64:Number 8(2017)
• Page Start: 613
• Page End: 627
• Publication Date: 2018-01-22
• Subjects: augmented probability simulation -- decision analysis -- endogenous uncertainty -- nested sampling -- stochastic programming; Logistics, Naval -- Periodicals; Supplies and stores -- Periodicals; 359.07
• DOI: 10.1002/nav.21778
• Languages: English
• ISSNs: 0894-069X

Abstract

Abstract: We propose a novel simulation‐based approach for solving two‐stage stochastic programs with recourse and endogenous (decision dependent) uncertainty. The proposed augmented nested sampling approach recasts the stochastic optimization problem as a simulation problem by treating the decision variables as random. The optimal decision is obtained via the mode of the augmented probability model. We illustrate our methodology on a newsvendor problem with stock‐dependent uncertain demand both in single and multi‐item (news‐stand) cases. We provide performance comparisons with Markov chain Monte Carlo and traditional Monte Carlo simulation‐based optimization schemes. Finally, we conclude with directions for future research.