论文信息 - On Bayesian inference for the M/G/1 queue with efficient MCMC sampling

On Bayesian inference for the M/G/1 queue with efficient MCMC sampling

We introduce an efficient MCMC sampling scheme to perform Bayesian inference in the M/G/1 queueing model given only observations of interdeparture times. Our MCMC scheme uses a combination of Gibbs sampling and simple Metropolis updates together with three novel "shift" and "scale" updates. We show that our novel updates improve the speed of sampling considerably, by factors of about 60 to about 180 on a variety of simulated data sets.

Radford M. Neal | Alexander Y. Shestopaloff

[1] N. Metropolis,et al. Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[2] T. Amemiya. Non-linear regression models , 1983 .

[3] Radford M. Neal,et al. Inferring State Sequences for Non-linear Systems with Embedded Hidden Markov Models , 2003, NIPS.

[4] Radford M. Neal. Markov Chain Sampling for Non-linear State Space Models Using Embedded Hidden Markov Models , 2003, math/0305039.

[5] C. Geyer. The Metropolis-Hastings-Green Algorithm , 2005 .

[6] Paul Fearnhead,et al. Constructing Summary Statistics for Approximate Bayesian Computation: Semi-automatic ABC , 2010, 1004.1112.

[7] Olivier François,et al. Non-linear regression models for Approximate Bayesian Computation , 2008, Stat. Comput..

[8] Radford M. Neal. Probabilistic Inference Using Markov Chain Monte Carlo Methods , 2011 .

[9] Fernando V. Bonassi. Approximate Bayesian computation for complex dynamic systems , 2013 .

[10] Radford M. Neal,et al. MCMC for non-Linear State Space Models Using Ensembles of Latent Sequences , 2013 .

[11] M. Li,et al. Particle Markov chain Monte Carlo methods , 2015 .