Efficient Monte Carlo for high excursions of Gaussian random fields (Q433910): Difference between revisions
From MaRDI portal
Created a new Item |
Set OpenAlex properties. |
||
(5 intermediate revisions by 4 users not shown) | |||
Property / review text | |||
The authors of this paper deal with Monte Carlo methods and continuous Gaussian random fields of the form \(f: T\times \Omega\rightarrow \mathbb{R}\) over a \(d\)-dimensional compact set \(T\subset \mathbb{R}^d\). To be more precise, the paper deals with the design and analysis of Monte Carlo methods for computing tail probabilities of the form \[ w(b)=\text{P}(\max_{t\in T} f(t)>b), \] and conditional expectations \[ \text{E}(\Gamma(f)|\max_{t\in T} f(t)>b), \] as \(b\rightarrow \infty\), where \(\Gamma\) is a positive and bounded functional of the field. Estimating these probabilities and conditional expectations accurately (in relative terms) by the use of an approach using naive Monte Carlo would require a computational cost that is exponential in \(b\). However, in this paper, the authors introduce simulation estimators that work for a general class of Gaussian fields (assuming that the mean and covariance functions are Hölder continuous) and require at most a polynomial number of function evalutations in \(b\). Under the assumption of additional smoothness, this result can be further improved to estimators that are strongly efficient, by which is meant that their associated coefficient of variation is uniformly bounded as \(b\) tends to infinity. | |||
Property / review text: The authors of this paper deal with Monte Carlo methods and continuous Gaussian random fields of the form \(f: T\times \Omega\rightarrow \mathbb{R}\) over a \(d\)-dimensional compact set \(T\subset \mathbb{R}^d\). To be more precise, the paper deals with the design and analysis of Monte Carlo methods for computing tail probabilities of the form \[ w(b)=\text{P}(\max_{t\in T} f(t)>b), \] and conditional expectations \[ \text{E}(\Gamma(f)|\max_{t\in T} f(t)>b), \] as \(b\rightarrow \infty\), where \(\Gamma\) is a positive and bounded functional of the field. Estimating these probabilities and conditional expectations accurately (in relative terms) by the use of an approach using naive Monte Carlo would require a computational cost that is exponential in \(b\). However, in this paper, the authors introduce simulation estimators that work for a general class of Gaussian fields (assuming that the mean and covariance functions are Hölder continuous) and require at most a polynomial number of function evalutations in \(b\). Under the assumption of additional smoothness, this result can be further improved to estimators that are strongly efficient, by which is meant that their associated coefficient of variation is uniformly bounded as \(b\) tends to infinity. / rank | |||
Normal rank | |||
Property / reviewed by | |||
Property / reviewed by: Peter Kritzer / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 60G15 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 65C05 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 60G60 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62G32 / rank | |||
Normal rank | |||
Property / zbMATH DE Number | |||
Property / zbMATH DE Number: 6053742 / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
Gaussian random fields | |||
Property / zbMATH Keywords: Gaussian random fields / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
high-level excursions | |||
Property / zbMATH Keywords: high-level excursions / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
Monte Carlo | |||
Property / zbMATH Keywords: Monte Carlo / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
tail distributions | |||
Property / zbMATH Keywords: tail distributions / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
efficiency | |||
Property / zbMATH Keywords: efficiency / rank | |||
Normal rank | |||
Property / MaRDI profile type | |||
Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank | |||
Property / arXiv ID | |||
Property / arXiv ID: 1005.0812 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q3935962 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Stochastic modelling in physical oceanography / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Random Fields and Geometry / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Stochastic simulation: Algorithms and analysis / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Level Sets and Extrema of Random Processes and Fields / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4023200 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Efficient importance sampling for binary contingency tables / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: The Brunn-Minkowski inequality in Gauss space / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Introduction to rare event simulation. / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4131354 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Sample functions of the Gaussian process / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4114580 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q2774021 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q5623005 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Extremes and related properties of random sequences and processes / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Probability and Computing / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Fixed Precision MCMC Estimation by Median of Products of Averages / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: The Poisson bracket for \(2\)D hydrodynamics reduces to the Gardner bracket / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Validity of the expected Euler characteristic heuristic / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Detecting Sparse Signals in Random Fields, With an Application to Brain Mapping / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4040428 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: The Density of the Distribution of the Maximum of a Gaussian Process / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4389415 / rank | |||
Normal rank | |||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W2141159152 / rank | |||
Normal rank | |||
links / mardi / name | links / mardi / name | ||
Latest revision as of 10:46, 30 July 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Efficient Monte Carlo for high excursions of Gaussian random fields |
scientific article |
Statements
Efficient Monte Carlo for high excursions of Gaussian random fields (English)
0 references
8 July 2012
0 references
The authors of this paper deal with Monte Carlo methods and continuous Gaussian random fields of the form \(f: T\times \Omega\rightarrow \mathbb{R}\) over a \(d\)-dimensional compact set \(T\subset \mathbb{R}^d\). To be more precise, the paper deals with the design and analysis of Monte Carlo methods for computing tail probabilities of the form \[ w(b)=\text{P}(\max_{t\in T} f(t)>b), \] and conditional expectations \[ \text{E}(\Gamma(f)|\max_{t\in T} f(t)>b), \] as \(b\rightarrow \infty\), where \(\Gamma\) is a positive and bounded functional of the field. Estimating these probabilities and conditional expectations accurately (in relative terms) by the use of an approach using naive Monte Carlo would require a computational cost that is exponential in \(b\). However, in this paper, the authors introduce simulation estimators that work for a general class of Gaussian fields (assuming that the mean and covariance functions are Hölder continuous) and require at most a polynomial number of function evalutations in \(b\). Under the assumption of additional smoothness, this result can be further improved to estimators that are strongly efficient, by which is meant that their associated coefficient of variation is uniformly bounded as \(b\) tends to infinity.
0 references
Gaussian random fields
0 references
high-level excursions
0 references
Monte Carlo
0 references
tail distributions
0 references
efficiency
0 references