Informed proposals for local MCMC in discrete spaces

@inproceedings{Zanella2017InformedPF,
  title={Informed proposals for local MCMC in discrete spaces},
  author={Giacomo Zanella},
  year={2017}
}
  • Giacomo Zanella
  • Published 2017
  • Mathematics
  • There is a lack of methodological results to design efficient Markov chain Monte Carlo (MCMC) algorithms for statistical models with discrete-valued high-dimensional parameters. Motivated by this consideration, we propose a simple framework for the design of informed MCMC proposals (i.e. Metropolis-Hastings proposal distributions that appropriately incorporate local information about the target) which is naturally applicable to both discrete and continuous spaces. We explicitly characterize the… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    2
    Twitter Mentions

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 12 CITATIONS

    Lifted samplers for partially ordered discrete state-spaces

    VIEW 13 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    A step further towards automatic and efficient reversible jump algorithms

    VIEW 9 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Exploring Discrete Analogs of Hamiltonian Monte Carlo

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Estimating Convergence of Markov chains with L-Lag Couplings

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    The Hamming Ball Sampler

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    An external field prior for the hidden Potts model with application to cone-beam computed tomography

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Auxiliary-variable Exact Hamiltonian Monte Carlo Samplers for Binary Distributions

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL

    Markov Chains and Mixing Times

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    Record linkage: statistical models for matching computer records.

    • John Copas, F J Hilton
    • Mathematics, Geography, Medicine
    • Journal of the Royal Statistical Society. Series A,
    • 1990
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL