Adaptively Scaling the Metropolis Algorithm Using Expected Squared Jumped Distance

137 citations recorded by the source corpus.

How researchers see this paper

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

Generalizing Hamiltonian Monte Carlo with Neural Networks (2017, methodology): “This is equivalent to maximizing expected squared jumped distance [17].”
Bayesian inference for irreducible diffusion processes using the pseudo-marginal approach (2011, methodology): “Pedersen (1995) proposed the Euler sampler q(u) = ∏M−2 m=0 φ(um+1;um + hμ(Um, θ), hν(Um, θ)) for (1).”
MCMC algorithms for Subset Simulation (2015, unknown): “(22) (e.g. Pasarica & Gelman 2010).”
An Adaptive Sequential Monte Carlo Sampler (2010, methodology): “Maximising the ESJD is equivalent to minimising the lag-1 autocorrelation; this measure is often used within adaptive MCMC, see for example Sherlock and Roberts (2009); Pasarica and Gelman (2010).”
Optimal tuning of the hybrid Monte Carlo algorithm (2010, unknown): “This measure of efficiency is a fairly standard one; see [8,34], for example.”
Accelerating Markov Chain Monte Carlo Simulation by Differential Evolution with Self-Adaptive Randomized Subspace Sampling (2009, methodology): “A similar idea using the expected squared jumped distance is presented in [30].”