Efficient Monte Carlo for high excursions of Gaussian random fields

DOI10.1214/11-AAP792zbMATH Open1251.60031arXiv1005.0812OpenAlexW2141159152MaRDI QIDQ433910FDOQ433910

Authors: Robert J. Adler, Jose Blanchet, Jingchen Liu 

Publication date: 8 July 2012

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Abstract: Our focus is on the design and analysis of efficient Monte Carlo methods for computing tail probabilities for the suprema of Gaussian random fields, along with conditional expectations of functionals of the fields given the existence of excursions above high levels, b. Na"{i}ve Monte Carlo takes an exponential, in b, computational cost to estimate these probabilities and conditional expectations for a prescribed relative accuracy. In contrast, our Monte Carlo procedures achieve, at worst, polynomial complexity in b, assuming only that the mean and covariance functions are H"{o}lder continuous. We also explain how to fine tune the construction of our procedures in the presence of additional regularity, such as homogeneity and smoothness, in order to further improve the efficiency.

Full work available at URL: https://arxiv.org/abs/1005.0812

Recommendations

• Efficient conditional Monte Carlo simulations for the exponential integrals of Gaussian random fields
• Uniformly efficient simulation for extremes of Gaussian random fields
• Efficient simulations for the exponential integrals of Hölder continuous Gaussian random fields
• Fast simulation of Gaussian random fields
• Efficiency of Monte Carlo computations in very high dimensional spaces
• On the conditional distributions and the efficient simulations of exponential integrals of Gaussian random fields
• Fast sampling of parameterised Gaussian random fields
• Population Monte Carlo algorithm in high dimensions
• Efficient Monte Carlo simulation for integral functionals of Brownian motion
• Monte Carlo gradient estimation in high dimensions

zbMATH Keywords

Gaussian random fieldsMonte Carloefficiencyhigh-level excursionstail distributions

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Gaussian processes (60G15) Random fields (60G60) Statistics of extreme values; tail inference (62G32)

Cites Work

• Extremes and related properties of random sequences and processes
• Title not available (Why is that?)
• Title not available (Why is that?)
• Stochastic simulation: Algorithms and analysis
• Level Sets and Extrema of Random Processes and Fields
• Random Fields and Geometry
• The Brunn-Minkowski inequality in Gauss space
• Validity of the expected Euler characteristic heuristic
• Title not available (Why is that?)
• Introduction to rare event simulation.
• The Density of the Distribution of the Maximum of a Gaussian Process
• Title not available (Why is that?)
• Title not available (Why is that?)
• Probability and Computing
• Detecting Sparse Signals in Random Fields, With an Application to Brain Mapping
• Title not available (Why is that?)
• Fixed Precision MCMC Estimation by Median of Products of Averages
• Sample functions of the Gaussian process
• Title not available (Why is that?)
• Stochastic modelling in physical oceanography
• The Poisson bracket for \(2\)D hydrodynamics reduces to the Gardner bracket
• Efficient importance sampling for binary contingency tables
• Title not available (Why is that?)

Cited In (29)

• Importance sampling the union of rare events with an application to power systems analysis
• Some asymptotic results of Gaussian random fields with varying mean functions and the associated processes
• High-frequency asymptotics for Lipschitz-Killing curvatures of excursion sets on the sphere
• Quantifying uncertainties on excursion sets under a Gaussian random field prior
• The harmonic mean formula for random processes
• Uniformly efficient simulation for extremes of Gaussian random fields
• Large excursion probabilities for random fields close to Gaussian ones
• The stochastic collocation Monte Carlo sampler: highly efficient sampling from ‘expensive’ distributions
• Moderate deviation for random elliptic PDE with small noise
• Efficient conditional Monte Carlo simulations for the exponential integrals of Gaussian random fields
• Extreme analysis of a random ordinary differential equation
• On the density functions of integrals of Gaussian random fields
• On Piterbarg max-discretisation theorem for standardised maximum of stationary Gaussian processes
• Efficient rare event simulation for failure problems in random media
• Speeding up Monte Carlo simulations for the adaptive sum of powered score test with importance sampling
• Rare-event simulation and efficient discretization for the supremum of Gaussian random fields
• Efficient simulations for the exponential integrals of Hölder continuous Gaussian random fields
• Rare-event simulation for neural network and random forest predictors
• Chernoff index for Cox test of separate parametric families
• Asymptotically Optimal Sequential Design for Rank Aggregation
• The convergence rate and asymptotic distribution of the bootstrap quantile variance estimator for importance sampling
• Rare-event simulation for distribution networks
• Tail approximations of integrals of Gaussian random fields
• On the conditional distributions and the efficient simulations of exponential integrals of Gaussian random fields
• Recovering best statistical guarantees via the empirical divergence-based distributionally robust optimization
• Generalized Sequential Probability Ratio Test for Separate Families of Hypotheses
• Efficient simulation for dependent rare events with applications to extremes
• Editorial introduction: special issue on Gaussian queues
• Efficient simulation for the maximum of infinite horizon discrete-time Gaussian processes

This page was built for publication: Efficient Monte Carlo for high excursions of Gaussian random fields

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q433910)