Exact bound for the convergence of metropolis chains
From MaRDI portal
Publication:4946979
This paper presents the exact bound for the rate of convergence of Metropolis chains in a finite state space which improves the previous results about the rates of convergence of Metropolis algorithm due to \textit{K. L. Mengersen} and \textit{R. L. Tweedie} [Ann. Stat. 24, No. 1, 101-121 (1996; Zbl 0854.60065)] where only the upper bound of such convergence is obtained. The main result is proved by application of the properties of the transition probabilities and eigenvalues of Metropolis chains.
Recommendations
- On the rate of convergence of the Metropolis algorithm and Gibbs sampler by geometric bounds
- Markov chain convergence: From finite to infinite
- Rates of convergence of the Hastings and Metropolis algorithms
- Spectral gaps of random walk Metropolis chains
- Conductance bounds on the L2 convergence rate of Metropolis algorithms on unbounded state spaces
Cited in
(9)- On the rate of convergence of the Metropolis algorithm and Gibbs sampler by geometric bounds
- Markov chain convergence: From finite to infinite
- On constrained simulation and optimization by Metropolis chains
- A hybrid Metropolis-Hastings chain
- Spectral gaps of random walk Metropolis chains
- Metropolis
- Conductance bounds on the L2 convergence rate of Metropolis algorithms on unbounded state spaces
- One-pass additive-error subset selection for \(\ell_p\) subspace approximation and \((k, p)\)-clustering
- Explicit convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles
This page was built for publication: Exact bound for the convergence of metropolis chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4946979)