Kriging-Aided Cross-Entropy-Based Adaptive Importance Sampling Using Gaussian Mixture

2018 ◽  
Vol 43 (S1) ◽  
pp. 81-88
Author(s):  
Moien Barkhori ◽  
Mohsen Ali Shayanfar ◽  
Mohammad Ali Barkhordari ◽  
Taha Bakhshpoori
Keyword(s):  
Importance Sampling ◽  
Gaussian Mixture ◽  
Cross Entropy ◽  
Adaptive Importance Sampling

scholarly journals A comparison of cross-entropy and variance minimization strategies

2011 ◽  
Vol 48 (A) ◽  
pp. 183-194 ◽  
Author(s):  
Joshua C. C. Chan ◽  
Peter W. Glynn ◽  
Dirk P. Kroese
Keyword(s):  
Importance Sampling ◽  
Rare Event ◽  
Cross Entropy ◽  
Variance Minimization ◽  
Adaptive Importance Sampling ◽  
Estimation Problems ◽  
Sampling Procedures

The variance minimization (VM) and cross-entropy (CE) methods are two versatile adaptive importance sampling procedures that have been successfully applied to a wide variety of difficult rare-event estimation problems. We compare these two methods via various examples where the optimal VM and CE importance densities can be obtained analytically. We find that in the cases studied both VM and CE methods prescribe the same importance sampling parameters, suggesting that the criterion of minimizing the CE distance is very close, if not asymptotically identical, to minimizing the variance of the associated importance sampling estimator.

scholarly journals A comparison of cross-entropy and variance minimization strategies

2011 ◽  
Vol 48 (A) ◽  
pp. 183-194 ◽  
Author(s):  
Joshua C. C. Chan ◽  
Peter W. Glynn ◽  
Dirk P. Kroese
Keyword(s):  
Importance Sampling ◽  
Rare Event ◽  
Cross Entropy ◽  
Variance Minimization ◽  
Adaptive Importance Sampling ◽  
Estimation Problems ◽  
Sampling Procedures

The variance minimization (VM) and cross-entropy (CE) methods are two versatile adaptive importance sampling procedures that have been successfully applied to a wide variety of difficult rare-event estimation problems. We compare these two methods via various examples where the optimal VM and CE importance densities can be obtained analytically. We find that in the cases studied both VM and CE methods prescribe the same importance sampling parameters, suggesting that the criterion of minimizing the CE distance is very close, if not asymptotically identical, to minimizing the variance of the associated importance sampling estimator.

Sign in / Sign up

Export Citation Format

Share Document