Management Science and Financial Engineering

The Korean Operations Research and Management Science Society (한국경영과학회)
권호 표지
DOI QR코드

DOI QR Code

Improved MCMC Simulation for Low-Dimensional Multi-Modal Distributions

  • Ji, Hyunwoong (Department of Industrial Engineering, Seoul National University) ;
  • Lee, Jaewook (Department of Industrial Engineering, Seoul National University) ;
  • Kim, Namhyoung (Department of Industrial Engineering, Seoul National University)
  • Received : 2013.10.30
  • Accepted : 2013.11.11
  • Published : 2013.11.22
Download PDF
⟨ Previous Next ⟩

Abstract

A Markov-chain Monte Carlo sampling algorithm samples a new point around the latest sample due to the Markov property, which prevents it from sampling from multi-modal distributions since the corresponding chain often fails to search entire support of the target distribution. In this paper, to overcome this problem, mode switching scheme is applied to the conventional MCMC algorithms. The algorithm separates the reducible Markov chain into several mutually exclusive classes and use mode switching scheme to increase mixing rate. Simulation results are given to illustrate the algorithm with promising results.

Keywords

References

  1. Andrieu, C. and N. de Freitas, A. Doucet, and M. Jordan, "An Introduction to MCMC for Machine Learning," Machine Learning 50, 1/2 (2003), 5-43. https://doi.org/10.1023/A:1020281327116
  2. Binder, K. and D. W. Heermann, "Monte Carlo simulation in statistical physics: an introduction," Springer, 2010.
  3. Cowles, M. K. and B. P. Carlin, "Markov Chain Monte Carlo Convergence Diagnostics: A Comparative Review," Journal of the American Statistical Association 91, 434 (1996), 883-904. https://doi.org/10.1080/01621459.1996.10476956
  4. Epanechnikov, V., "Non-Parametric Estimation of a Multivariate Probability Density," Theory of Probability and Its Applications 14, 1 (1969), 153-158. https://doi.org/10.1137/1114019
  5. Kalogeropoulos, K., G. Roberts, and P. Dellaportas, "Irreducible Markov Chain Monte Carlo Schemes for Partially Observed Diffusions," Nonlinear Statistical Signal Processing Workshop, IEEE, (2006) 216-219.
  6. Kim, N. and J. Lee, "No-arbitrage implied volatility functions: Empirical evidence from KOSPI 200 index options," Journal of Empirical Finance 21 (2013), 36-53. https://doi.org/10.1016/j.jempfin.2012.12.007
  7. Rannala, B., "Identifiability of Parameters in MCMC Bayesian Inference of Phylogeny," Systematic Biology 51, 5 (2002), 754-760. https://doi.org/10.1080/10635150290102429
  8. Roberts, G. O. and O. Stramer, "Langevin Diffusions and Metropolis-Hastings Algorithms," Methodology And Computing In Applied Probability 4, 4 (2002), 337-357. https://doi.org/10.1023/A:1023562417138