Faster Adaptive Importance Sampling in Low Dimensions
| Autor: | Gary W. Oehlert |
|---|---|
| Rok vydání: | 1998 |
| Předmět: |
Statistics and Probability
Mathematical optimization Kernel density estimation Bandwidth (signal processing) Multivariate kernel density estimation Spline (mathematics) Kernel embedding of distributions Variable kernel density estimation Discrete Mathematics and Combinatorics Mixture distribution Statistics Probability and Uncertainty Algorithm Importance sampling Mathematics |
| Zdroj: | Journal of Computational and Graphical Statistics. 7:158-174 |
| ISSN: | 1537-2715 1061-8600 |
| DOI: | 10.1080/10618600.1998.10474768 |
| Popis: | Adaptive importance sampling using kernel density estimation techniques was introduced by West. This technique adapts the importance sampling function to the underlying integrand, thus yielding small-variance estimates. One drawback of this approach is that evaluation of the kernel mixture density is slow. We present a linear tensor spline representation of the adaptive importance function using variable bandwidth kernels that retains the small variance properties of West's approach but executes more quickly. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|