Norges Teknisk-naturvitenskapelige Universitet Control Variates for the Metropolis-hastings Algorithm Control Variates for the Metropolis-hastings Algorithm
By Hugo Lewi Hammer, Håkon Tjelmeland
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Petros Dellaportas
- François‐Xavier Briol
- Nicolas Chopin
- Jon Cockayne
- Ioannis Kontoyiannis
- Chris J. Oates
- Paul Fearnhead
- Randal Douc
Citations in the corpus
- Control functionals for Monte Carlo integration (2014, background): “For continuous state spaces, statistics relating to the chain can be used as control variates (Hammer and Tjelmeland, 2008; Dellaportas and Kontoyiannis, 2012; Li et al., 2016).”
- Zero Variance Differential Geometric Markov Chain Monte Carlo Algorithms (2014, background): “Atchadé and Perron (2005) build control variates for independent Metropolis-Hastings samplers, while Hammer and Tjemeland (2008) introduce control variates for general Metropolis-Hastings samplers.”
- The Controlled Thermodynamic Integral for Bayesian Model Comparison (2014, background): “y associated with the solution of the Poisson equation h() = E ˇ[g()] g() and proposing to solve this equation numerically. Further work on constructing control variates for Markov chains includes Hammer and Tjelmeland (2008) for Metropolis-Hasings chains and 5 Dellaportas and Kontoyiannis (2012) fo”
- Control variates for estimation based on reversible Markov chain Monte Carlo samplers (2012, methodology): “Like Hammer and Tjelmeland (2008), Delmas and Jourdain expanded the state space to include the proposals and they first took G=F and θ= 1 (which, in part, explains why their waste recycling algorithm is sometimes worse than plain Metropolis sampling).”
- Exploiting Multi-Core Architectures for Reduced-Variance Estimation with Intractable Likelihoods (2014, unknown): “Further work to construct control variates for Markov chains includes Hammer and Tjelmeland (2008) for Metropolis–Hastings samplers and Dellaportas and Kontoyiannis (2012) for Gibbs samplers.”
- 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].”