A Control Variate Approach for Improving Efficiency of Ensemble Monte Carlo - Computer Science > Computational Engineering, Finance, and ScienceReport as inadecuate




A Control Variate Approach for Improving Efficiency of Ensemble Monte Carlo - Computer Science > Computational Engineering, Finance, and Science - Download this document for free, or read online. Document in PDF available to download.

Abstract: In this paper we present a new approach to control variates for improvingcomputational efficiency of Ensemble Monte Carlo. We present the approach usingsimulation of paths of a time-dependent nonlinear stochastic equation. The coreidea is to extract information at one or more nominal model parameters and usethis information to gain estimation efficiency at neighboring parameters. Thisidea is the basis of a general strategy, called DataBase Monte Carlo DBMC,for improving efficiency of Monte Carlo. In this paper we describe how thisstrategy can be implemented using the variance reduction technique of ControlVariates CV. We show that, once an initial setup cost for extractinginformation is incurred, this approach can lead to significant gains incomputational efficiency. The initial setup cost is justified in projects thatrequire a large number of estimations or in those that are to be performedunder real-time constraints.



Author: T. Borogovac, F. J. Alexander, P. Vakili

Source: https://arxiv.org/







Related documents