In this article, we consider a Gaussian random field f (t) living on a compact set T ⊂ Rd and the computation of the tail probabilities P(∫ T e f (t)dt > eb) as b→∞. We design asymptotically efficient importance sampling estimators for a general class of Hölder continuous Gaussian random fields. In addition to the variance control, we also analyze the bias (relative to the interesting tail probabilities) caused by the discretization.
|Original language||English (US)|
|Journal||ACM Transactions on Modeling and Computer Simulation|
|State||Published - Feb 2014|
- Exponential integral
- Gaussian random fields
- Importance sampling