Control functionals for Monte Carlo integration
From MaRDI portal
Publication:5743239
Abstract: A non-parametric extension of control variates is presented. These leverage gradient information on the sampling density to achieve substantial variance reduction. It is not required that the sampling density be normalised. The novel contribution of this work is based on two important insights; (i) a trade-off between random sampling and deterministic approximation and (ii) a new gradient-based function space derived from Stein's identity. Unlike classical control variates, our estimators achieve super-root- convergence, often requiring orders of magnitude fewer simulations to achieve a fixed level of precision. Theoretical and empirical results are presented, the latter focusing on integration problems arising in hierarchical models and models based on non-linear ordinary differential equations.
Recommendations
- Monte Carlo integration with a growing number of control variates
- Control variate selection for Monte Carlo integration
- Control Variates for Monte Carlo Analysis of Nonlinear Statistical Models, I: Overview
- Control Variates for Estimation Based on Reversible Markov Chain Monte Carlo Samplers
- scientific article; zbMATH DE number 1911041
Cited in
(40)- Monte Carlo gradient estimation in machine learning
- Diffusion approximations and control variates for MCMC
- Bayesian quadrature, energy minimization, and space-filling design
- Convergence rates for a class of estimators based on Stein's method
- Regularized zero-variance control variates
- Performance analysis of greedy algorithms for minimising a maximum mean discrepancy
- Monte Carlo with determinantal point processes
- Optimal Monte Carlo integration on closed manifolds
- Variance reduction for additive functionals of Markov chains via martingale representations
- Learning effective state-feedback controllers through efficient multilevel importance samplers
- Using the Monte Carlo method to solve integral equations using a modified control variate
- Probabilistic integration: a role in statistical computation?
- A Riemann-Stein kernel method
- Monte Carlo integration with a growing number of control variates
- Adaptive importance sampling and control variates
- The Matérn model: a journey through statistics, numerical analysis and machine learning
- Scalable Control Variates for Monte Carlo Methods Via Stochastic Optimization
- Measuring sample quality with diffusions
- Indirect inference for time series using the empirical characteristic function and control variates
- Variance reduction for dependent sequences with applications to stochastic gradient MCMC
- Variance reduction for Markov chains with application to MCMC
- Data-driven low-fidelity models for multi-fidelity Monte Carlo sampling in plasma micro-turbulence analysis
- Empirical variance minimization with applications in variance reduction and optimal control
- Collocation methods and beyond in non-linear mechanics
- Correlations between random projections and the bivariate normal
- Adaptive experiment design for probabilistic integration
- Control variate selection for Monte Carlo integration
- A general framework for empirical Bayes estimation in discrete linear exponential family
- Importance sampling in reinforcement learning with an estimated behavior policy
- Globally adaptive control variate for robust numerical integration
- Deterministic Sampling of Expensive Posteriors Using Minimum Energy Designs
- Stein's method meets computational statistics: a review of some recent developments
- Risk bounds when learning infinitely many response functions by ordinary linear regression
- Multifidelity Monte Carlo Estimation with Adaptive Low-Fidelity Models
- A generalized approximate control variate framework for multifidelity uncertainty quantification
- Variance reduction in Monte Carlo estimators via empirical variance minimization
- Asymptotic variance for random walk Metropolis chains in high dimensions: logarithmic growth via the Poisson equation
- scientific article; zbMATH DE number 7164690 (Why is no real title available?)
- A Perturbative Approach to Control Variates in Molecular Dynamics
- Variance reduction for Metropolis-Hastings samplers
This page was built for publication: Control functionals for Monte Carlo integration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5743239)
