Variance reduction through smoothing and control variates for Markov chain simulations

By Sigrún Andradóttir, D. Heyman, T. Ott. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Control functionals for Monte Carlo integration (2014, methodology): “For estimation based on Markov chains, control variates for the discrete state space case were provided by Andradóttir et al. (1993).”
Zero Variance Differential Geometric Markov Chain Monte Carlo Algorithms (2014, background): “Andradóttir et al. (1993) observe that the optimum variance reduction of discrete-time finite-state Markov chains can be attained via the solution of the Poisson equation.”
Exploiting Multi-Core Architectures for Reduced-Variance Estimation with Intractable Likelihoods (2014, methodology): “For estimation based on Markov chains, Andradóttir et al. (1993) proposed control variates for discrete state spaces. Later Mira et al. (2003) extended the approach of Assaraf and Caffarel (1999) observing that the optimal choice of h(θ) is intimately associated”
The Controlled Thermodynamic Integral for Bayesian Model Comparison (2014, methodology): “For estimation based on Markov chains, Andradóttir et al. (1993) proposed control variates for discrete state spaces.”
Convergence rates for a class of estimators based on Stein’s method (2016, background): “In this direction, the problem of constructing control variates for discrete state spaces was essentially solved by [1] and for continuous state spaces, recent contributions include [14,20,22, 29,30].”
Control variates for estimation based on reversible Markov chain Monte Carlo samplers (2012, methodology): “U/: .34/ This methodology has been used extensively in the literature, including, among others, by Andradòttir et al. (1993), Mira et al. (2003), Stein et al. (2004), Meyn (2007) and Hammer and Tjelmeland (2008).”