Monte Carlo integration with a growing number of control variates

DOI10.1017/JPR.2019.78zbMATH Open1427.60048arXiv1801.01797OpenAlexW2995883131MaRDI QIDQ5205948FDOQ5205948

Authors: François Portier, Johan Segers 

Publication date: 17 December 2019

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

Abstract: It is well known that Monte Carlo integration with variance reduction by means of control variates can be implemented by the ordinary least squares estimator for the intercept in a multiple linear regression model. A central limit theorem is established for the integration error if the number of control variates tends to infinity. The integration error is scaled by the standard deviation of the error term in the regression model. If the linear span of the control variates is dense in a function space that contains the integrand, the integration error tends to zero at a rate which is faster than the square root of the number of Monte Carlo replicates. Depending on the situation, increasing the number of control variates may or may not be computationally more efficient than increasing the Monte Carlo sample size.

Full work available at URL: https://arxiv.org/abs/1801.01797

Recommendations

• Control variate selection for Monte Carlo integration
• Control Functionals for Monte Carlo Integration
• Using the Monte Carlo method to solve integral equations using a modified control variate
• Monte Carlo, Control Variates, and Stochastic Ordering
• scientific article; zbMATH DE number 4013851
• Monte Carlo simulation of stochastic integrals when the cost of function evaluation is dimension dependent
• A Monte Carlo method for integration of multivariate smooth functions
• Variance analysis for Monte Carlo integration
• On variance reducing multipliers for Monte Carlo integration
• Monte Carlo efficiency improvement by multiple sampling of conditioned integration variables

zbMATH Keywords

central limit theoremcontrol variatesmultiple linear regressionordinary least squaresLegendre polynomialpost-stratification

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Monte Carlo methods (65C05) Central limit and other weak theorems (60F05)

Cites Work

• Title not available (Why is that?)
• Robust Statistics
• Title not available (Why is that?)
• Probability. Theory and examples.
• Convergence rates and asymptotic normality for series estimators
• Generalized, linear, and mixed models
• Title not available (Why is that?)
• Title not available (Why is that?)
• Efficient Computing of Regression Diagnostics
• Title not available (Why is that?)
• Asymptotic Normality of Series Estimators for Nonparametric and Semiparametric Regression Models
• Distribution modulo one and Diophantine approximation
• Nonparametric Importance Sampling
• Control variate selection for Monte Carlo integration
• Control Functionals for Monte Carlo Integration
• Safe and Effective Importance Sampling
• Title not available (Why is that?)
• On the convergence rates of Legendre approximation
• Solving BSDE with Adaptive Control Variate
• Integral approximation by kernel smoothing
• On the weak convergence of the empirical conditional copula under a simplifying assumption
• Large Sample Properties of Weighted Monte Carlo Estimators
• Monte Carlo with determinantal point processes
• Control variates for probability and quantile estimation.
• Convergence rates for a class of estimators based on Stein's method
• Some results on the complexity of numerical integration

Cited In (13)

• Regularized zero-variance control variates
• Monte Carlo, Control Variates, and Stochastic Ordering
• Using the Monte Carlo method to solve integral equations using a modified control variate
• Scalable Control Variates for Monte Carlo Methods Via Stochastic Optimization
• Indirect inference for time series using the empirical characteristic function and control variates
• Some large-sample results on a modified Monte Carlo integration method
• Title not available (Why is that?)
• Correlations between random projections and the bivariate normal
• Automatic control variates for option pricing using neural networks
• Control variate selection for Monte Carlo integration
• Efficiency of Multivariate Control Variates in Monte Carlo Simulation
• Risk bounds when learning infinitely many response functions by ordinary linear regression
• The control variate integration algorithm for multivariate functions defined at scattered data points

This page was built for publication: Monte Carlo integration with a growing number of control variates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5205948)