Conductance bounds on the L2 convergence rate of Metropolis algorithms on unbounded state spaces

@inproceedings{Jarner2004ConductanceBO,
  title={Conductance bounds on the L2 convergence rate of Metropolis algorithms on unbounded state spaces},
  author={S{\o}ren Fiig Jarner and Wai Kong Yuen},
  year={2004}
}
In this paper we derive bounds on the conductance and hence on the spectral gap of a Metropolis algorithm with a monotone, log-concave target density on an interval of R .W e show that the minimal conductance set has measure 1 and we use this characterization to bound the conductance in terms of the conductance of the algorithm restricted to a smaller domain. Whereas previous work on conductance has resulted in good bounds for Markov chains on bounded domains, this is the first conductance… CONTINUE READING

Tables from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Applications of geometric bounds to the convergence rate of Markov chains on Rn

W. K. Yuen
  • Stoch. Process. Appl
  • 2000
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Polynomial and geometric convergence of Markov chains with applications to MCMC methods

S. F. Jarner
  • Doctoral Thesis , Lancaster University
  • 2001
VIEW 1 EXCERPT

Convergence of Probability Measures, 2nd edn

P. Billingsley
  • 1999
VIEW 1 EXCERPT