Scaling Limits for the Transient Phase of Local Metropolis-Hastings Algorithms

@inproceedings{Christensen2003ScalingLF,
  title={Scaling Limits for the Transient Phase of Local Metropolis-Hastings Algorithms},
  author={Ole F. Christensen and Gareth O. Roberts and Jeffrey S. Rosenthal},
  year={2003}
}
This paper considers high-dimensional Metropolis and Langevin algorithms in their initial transient phase. In stationarity, these algorithms are well-understood and it is now well-known how to scale their proposal distribution variances. For the random walk Metropolis algorithm, convergence during the transient phase is extremely regular to the extent that the algorithm’s sample path actually resembles a deterministic trajectory. In contrast, the Langevin algorithm with variance scaled to be… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
27 Citations
21 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 21 references

On the robustness of optimal scaling for Metropolis-Hastings algorithms

  • M. Bédard
  • Ph.D. dissertation, University of Toronto. Work…
  • 2004
Highly Influential
5 Excerpts

Markov processes: Characterization and Convergence

  • S. N. Ethier, T. G. Kurtz
  • 1986
Highly Influential
6 Excerpts

Optimal scaling for various MetropolisHastings algorithms

  • G. O. Roberts, J. S. Rosenthal
  • Statistical Science
  • 2001
Highly Influential
6 Excerpts

Optimal Metropolis algorithms for product measures on the vertices of a hypercube

  • G. O. Roberts
  • Stochastics and Stochastic Reports
  • 1998
Highly Influential
4 Excerpts

Exact likelihood-based estimation of diffusion processes

  • A. Beskos, O. Papaspiliopoulos, G. O. Roberts, Fearnhead P.N
  • 2004

Optimal scaling of Metropolis algorithms for discontinuous densities

  • G. O. Roberts, W. K. Yuen
  • Work in progress
  • 2004
2 Excerpts

Non - centered parameter - isations for hierarchical models and data augmentation

  • J. M. Bernardo, S. Bayarri, +4 authors G. O. Roberts
  • Bayesian statistics 7
  • 2003

Non-centered parameterisations for hierarchical models and data augmentation. In: Bayesian statistics 7 (eds

  • O. Papaspiliopoulos, G. O. Roberts, M. Sköld
  • 2003
2 Excerpts

Robust MCMC methods for spatial GLMM’s

  • O. F. Christensen, G. O. Roberts, M. Sköld
  • Technical Report 23,
  • 2003
3 Excerpts

Similar Papers

Loading similar papers…