Corpus ID: 5813204

A Level-set Hit-and-run Sampler for Quasi-Concave Distributions

@inproceedings{Jensen2014ALH,
  title={A Level-set Hit-and-run Sampler for Quasi-Concave Distributions},
  author={Shane T. Jensen and D. Foster},
  booktitle={AISTATS},
  year={2014}
}
  • Shane T. Jensen, D. Foster
  • Published in AISTATS 2014
  • Mathematics, Computer Science
  • We develop a new sampling strategy that uses the hit-and-run algorithm within level sets of a target density. Our method can be applied to any quasi-concave density, which covers a broad class of models. Standard sampling methods often perform poorly on densities that are high-dimensional or multi-modal. Our level set sampler performs well in high-dimensional settings, which we illustrate on a spike-and-slab mixture model. We also extend our method to exponentially-tilted quasi-concave… CONTINUE READING

    References

    SHOWING 1-10 OF 15 REFERENCES
    General Hit-and-Run Monte Carlo sampling for evaluating multidimensional integrals
    • 59
    The No-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo
    • 1,868
    • PDF
    Slice Sampling
    • 1,316
    Monte Carlo Sampling Methods Using Markov Chains and Their Applications
    • 12,328
    • Highly Influential
    • PDF
    Hit-and-run mixes fast
    • L. Lovász
    • Mathematics, Computer Science
    • Math. Program.
    • 1999
    • 214
    APPROACHES FOR BAYESIAN VARIABLE SELECTION
    • 1,123
    MCMC Using Hamiltonian Dynamics
    • 1,773
    • PDF
    Log-concave probability and its applications
    • 1,323
    • PDF
    Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
    • S. Geman, D. Geman
    • Mathematics, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 1984
    • 13,456
    • PDF
    WinBUGS - A Bayesian modelling framework: Concepts, structure, and extensibility
    • 5,220
    • PDF